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

    Neuronpedia

    INDEX
    Explanations

    amount or id usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    الق
    0.56
     jäl
    0.55
    wealth
    0.55
     harsh
    0.54
     true
    0.53
     future
    0.51
    কালের
    0.49
    active
    0.49
     strict
    0.49
    ddots
    0.49
    POSITIVE LOGITS
     городе
    0.95
     ਨੂੰ
    0.95
     Tahun
    0.94
     पालिका
    0.94
     Mpc
    0.93
     Performs
    0.90
    нений
    0.90
     рублей
    0.89
     ::=
    0.87
    ֨
    0.87
    Act Density 0.382%

    No Known Activations