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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     twitch
    -0.07
     nasty
    -0.06
     داده
    -0.06
    outing
    -0.06
    ();"
    -0.06
    -hit
    -0.06
    تبه
    -0.06
    好了
    -0.06
     Νο
    -0.06
    urf
    -0.06
    POSITIVE LOGITS
    igenous
    0.06
     DR
    0.06
    CLE
    0.06
     zákona
    0.06
     journalism
    0.06
     darling
    0.06
     Representation
    0.06
     Ric
    0.06
    Que
    0.06
     서울
    0.06
    Act Density 0.051%

    No Known Activations