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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     BJP
    -0.06
     Tul
    -0.06
    .updateDynamic
    -0.06
    estatus
    -0.06
     tvoří
    -0.06
    otřeb
    -0.06
     cz
    -0.06
    edith
    -0.06
    .er
    -0.06
     왕
    -0.06
    POSITIVE LOGITS
    AYS
    0.08
    CTIONS
    0.07
    _from
    0.07
    ays
    0.06
    Directed
    0.06
     campaigned
    0.06
     slogans
    0.06
    romo
    0.06
     reactionary
    0.06
     instructed
    0.06
    Act Density 0.001%

    No Known Activations