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

    Neuronpedia

    INDEX
    Explanations

    code definition and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fuelled
    0.44
    вого
    0.41
     needless
    0.41
    乃至
    0.39
    方
    0.39
    ホ
    0.39
    க்க
    0.38
     stage
    0.38
    ва
    0.37
    疲
    0.37
    POSITIVE LOGITS
    atthaya
    0.58
     большой
    0.50
     Punta
    0.49
    quirements
    0.48
    uanya
    0.48
    叁章
    0.48
    ommen
    0.48
    cemos
    0.47
    ières
    0.47
    макраты
    0.47
    Act Density 0.004%

    No Known Activations