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

    Neuronpedia

    INDEX
    Explanations

    boycotts and avoiding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     elections
    -0.06
    _network
    -0.06
     освіти
    -0.06
    imators
    -0.06
     produtos
    -0.06
    JR
    -0.06
     vote
    -0.06
     talked
    -0.06
    教育
    -0.06
     tier
    -0.06
    POSITIVE LOGITS
    /catalog
    0.07
    (lhs
    0.07
    .fil
    0.07
    \Twig
    0.06
    .black
    0.06
    Fizz
    0.06
    (errorMessage
    0.06
    _rect
    0.06
    [now
    0.06
    _videos
    0.06
    Act Density 0.027%

    No Known Activations