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

    Neuronpedia

    INDEX
    Explanations

    keywords related to instructions and notices about copyright and user agreements

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

    All ini, API requires, Allocate and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IC
    -0.36
    :
    -0.36
    ,
    -0.34
    ↵
    -0.33
    配
    -0.33
    Pick
    -0.31
     es
    -0.31
    Key
    -0.30
    Int
    -0.30
    ACE
    -0.30
    POSITIVE LOGITS
     мәкал
    1.12
     transfieras
    0.97
    الدراسه
    0.87
     nahilalakip
    0.84
     незавершена
    0.83
     zwiſchen
    0.83
     تضيفلها
    0.81
     Geſch
    0.80
     ſehr
    0.79
    <pad>
    0.79
    Act Density 0.007%

    No Known Activations