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

    Neuronpedia

    INDEX
    Explanations

    error messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     daydream
    0.78
     vetting
    0.78
     handling
    0.77
     हैंडल
    0.76
     万
    0.75
    võ
    0.75
    Yahoo
    0.75
    rceil
    0.74
     म्यूजिक
    0.74
     спорт
    0.73
    POSITIVE LOGITS
     message
    1.19
     mensagem
    1.12
    Message
    1.10
    message
    1.10
    MESSAGE
    1.09
     Message
    1.05
    getMessage
    1.00
    essage
    0.91
    メッセージ
    0.91
     mensagens
    0.90
    Act Density 0.130%

    No Known Activations