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

    Neuronpedia

    INDEX
    Explanations

    language switching

    np_acts-logits-general · gemini-2.5-flash-lite

    listing or organization markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    1.04
    8
    1.02
    ز
    0.99
    9
    0.91
    ı
    0.90
    in
    0.90
    1
    0.90
    在
    0.90
    મ
    0.89
    ม
    0.89
    POSITIVE LOGITS
    ActionsCallback
    0.72
     vakkh
    0.68
    IsResolver
    0.67
     खासा
    0.67
    穸
    0.67
    โมง
    0.66
     dhinak
    0.63
     և
    0.63
     طا
    0.62
    彠
    0.61
    Act Density 0.134%

    No Known Activations