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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate references or citations within a text

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

    "referred to as" definition phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cows
    -0.33
     chô
    -0.31
    BeginInit
    -0.31
    Jäh
    -0.30
    TargetException
    -0.30
     الحره
    -0.30
    Kariera
    -0.30
    在于
    -0.29
    gre
    -0.28
    leqslant
    -0.28
    POSITIVE LOGITS
     ब्रेकडाउन
    0.74
    Personendaten
    0.60
    UnusedPrivate
    0.57
     pinulongan
    0.57
    setVerticalGroup
    0.56
    addCriterion
    0.55
     Geraadpleegd
    0.54
    Autoritní
    0.54
     يتيمه
    0.54
    isance
    0.54
    Act Density 0.272%

    No Known Activations