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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     breach
    -0.07
    𝛽
    -0.07
    半个
    -0.06
    gain
    -0.06
    dance
    -0.06
     Hue
    -0.06
    يج
    -0.06
    istol
    -0.06
    .Category
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     Gund
    0.08
    Lng
    0.07
    Λ
    0.07
    煤炭
    0.07
    caster
    0.07
     всем
    0.07
    玙
    0.07
    ┣
    0.07
     Managed
    0.07
    总工会
    0.07
    Act Density 0.218%

    No Known Activations