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

    Neuronpedia

    INDEX
    Explanations

    d

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ंप
    -0.07
    лим
    -0.07
     fat
    -0.07
     xử
    -0.06
     lies
    -0.06
     pocházet
    -0.06
     десят
    -0.06
    wizard
    -0.06
    ratings
    -0.06
     ط
    -0.06
    POSITIVE LOGITS
     Draft
    0.07
    MSN
    0.07
    GPU
    0.06
    outh
    0.06
     biking
    0.06
     withObject
    0.06
     Oc
    0.06
    aimassage
    0.06
    remen
    0.06
     trial
    0.06
    Act Density 0.003%

    No Known Activations