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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating discrepancies, problems, or criticisms in a contextual analysis

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

    comparison with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.40
    ьажоргаш
    -0.39
     jScrollPane
    -0.38
    хьтан
    -0.38
     متعلقه
    -0.35
     lenker
    -0.35
     Италијани
    -0.35
    protoimpl
    -0.33
    LEncoder
    -0.32
     NSCoder
    -0.32
    POSITIVE LOGITS
    nicze
    0.51
    ſelf
    0.50
    UnusedPrivate
    0.49
    polation
    0.49
    QMetaType
    0.47
    carian
    0.47
    ſſel
    0.46
     ſont
    0.46
    ſelves
    0.46
    Selena
    0.45
    Act Density 0.290%

    No Known Activations