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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "F
    -0.07
     Pain
    -0.07
    ・・・
    -0.06
    Degree
    -0.06
     ModelRenderer
    -0.06
     compte
    -0.06
     &=
    -0.06
     X
    -0.06
     cứ
    -0.06
    اران
    -0.06
    POSITIVE LOGITS
     desirable
    0.07
     свя
    0.07
    .subscriptions
    0.06
    (getResources
    0.06
    _windows
    0.06
     rencontrer
    0.06
    ，却
    0.06
     عرضه
    0.06
    _sprites
    0.06
    лер
    0.06
    Act Density 0.006%

    No Known Activations