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

    Neuronpedia

    INDEX
    Explanations

    Thomas

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kog
    0.75
    sext
    0.70
    owania
    0.68
    wstring
    0.67
    namese
    0.66
     জব্দ
    0.66
    суль
    0.66
    संधान
    0.66
     Departamento
    0.65
    ogle
    0.65
    POSITIVE LOGITS
     kér
    0.69
     فه
    0.66
     கேட்ப
    0.65
     міс
    0.62
     FIS
    0.61
    Layer
    0.60
     PET
    0.60
    FIS
    0.59
    アス
    0.59
    ほどの
    0.58
    Act Density 0.001%

    No Known Activations