Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    discussions around theories and beliefs, especially when evaluating their validity or acceptance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Sentences ending with punctuation

    np_acts-logits-general · gemini-2.0-flash

    contrasting or incorrect statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    XmlAccessType
    -0.76
    DockStyle
    -0.64
    MemoryWarning
    -0.60
    Mediabestanden
    -0.59
    WriteBarrier
    -0.56
    ApiOperation
    -0.56
     PyObject
    -0.54
    resizingMask
    -0.53
    Hauptartikel
    -0.52
    addPreferredGap
    -0.51
    POSITIVE LOGITS
     Pourtant
    0.77
     Résultat
    0.60
     WRONG
    0.60
     जबकि
    0.59
    殊
    0.57
     Wrong
    0.57
     forgetting
    0.57
     wrong
    0.56
     falschen
    0.56
     оригіналу
    0.52
    Act Density 0.345%

    No Known Activations