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

    Neuronpedia

    INDEX
    Explanations

    occurrences of programming-related imports and package declarations

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

    ending with unusual characters

    np_acts-logits-general · gemini-2.0-flash

    apple, gov, apache, Pone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    -0.58
    –
    -0.54
    -
    -0.51
     “
    -0.50
    ogel
    -0.48
     (
    -0.48
     -
    -0.47
    gwin
    -0.47
     serupa
    -0.46
     but
    -0.46
    POSITIVE LOGITS
     يتيمه
    0.93
    neſs
    0.92
     houſe
    0.91
     Anſ
    0.91
    ſelf
    0.88
     pleaſure
    0.88
     Diſ
    0.87
     Houſe
    0.87
     Reſ
    0.87
     myſelf
    0.86
    Act Density 0.114%

    No Known Activations