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

    Neuronpedia

    INDEX
    Explanations

    rights

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    geom
    -0.07
     búsqueda
    -0.06
    cem
    -0.06
     timespec
    -0.06
     каль
    -0.06
     bazen
    -0.06
    几
    -0.06
    /original
    -0.06
     calculator
    -0.06
     suppl
    -0.06
    POSITIVE LOGITS
     rights
    0.12
    Rights
    0.11
     Rights
    0.10
     RIGHTS
    0.09
    rights
    0.08
    يت
    0.07
    рит
    0.07
    -rights
    0.07
    _subscribe
    0.07
    있는
    0.07
    Act Density 0.016%

    No Known Activations