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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and indicates the presence of errors in the code

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

    ; , -

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    جغرافيا
    -0.89
     Perſ
    -0.74
     للمعارف
    -0.73
     noqa
    -0.73
     חיצוניים
    -0.72
     Administrativna
    -0.72
     ſtand
    -0.70
     uſed
    -0.69
     ainfi
    -0.69
    IContainer
    -0.69
    POSITIVE LOGITS
     ad
    0.43
     he
    0.42
     ${\
    0.40
     paper
    0.40
    mapreduce
    0.39
     
    0.39
     radio
    0.39
    orphaned
    0.39
     man
    0.38
     imp
    0.38
    Act Density 0.018%

    No Known Activations