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

    Neuronpedia

    INDEX
    Explanations

    например

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ś
    -0.08
     Ś
    -0.07
    aju
    -0.06
     h
    -0.06
     �
    -0.06
     c
    -0.06
    isms
    -0.06
    =k
    -0.06
    AIL
    -0.06
     заліз
    -0.06
    POSITIVE LOGITS
     например
    0.26
     наприклад
    0.12
     například
    0.07
    岁
    0.07
    上传
    0.07
    -layout
    0.06
    責
    0.06
    UINT
    0.06
     sometimes
    0.06
    eer
    0.06
    Act Density 0.001%

    No Known Activations