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

    Neuronpedia

    INDEX
    Explanations

    say "record"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ()],
    -0.06
     ///</
    -0.06
    筑
    -0.06
     Designer
    -0.06
    .hash
    -0.06
    .*?)
    -0.06
     governance
    -0.06
    ,param
    -0.06
     nomination
    -0.06
     ignore
    -0.06
    POSITIVE LOGITS
     gays
    0.07
    ประส
    0.07
     Cameron
    0.06
     Clin
    0.06
    cao
    0.06
    .ACCESS
    0.06
    bou
    0.06
    iropr
    0.06
    рад
    0.06
     Christopher
    0.06
    Act Density 0.009%

    No Known Activations