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

    Neuronpedia

    INDEX
    Explanations

    user comments/answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    诱导
    -0.07
    .addTab
    -0.07
    gulp
    -0.06
    五六
    -0.06
    变得
    -0.06
    (nome
    -0.06
    史上最
    -0.06
    uced
    -0.06
     unmist
    -0.06
     swimming
    -0.06
    POSITIVE LOGITS
    مواجه
    0.07
     evasion
    0.07
     consolidate
    0.07
     protester
    0.06
     cooperation
    0.06
    ohan
    0.06
    ഷ
    0.06
    ଽ
    0.06
     eğlen
    0.06
     Blackhawks
    0.06
    Act Density 0.003%

    No Known Activations