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

    Neuronpedia

    INDEX
    Explanations

    foreign languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mono
    -0.07
     науки
    -0.07
     вне
    -0.06
     Durham
    -0.06
    Generally
    -0.06
     customary
    -0.06
     attainment
    -0.06
     titleLabel
    -0.06
     persona
    -0.06
     Deferred
    -0.06
    POSITIVE LOGITS
    _read
    0.07
    斗
    0.07
    XXX
    0.06
    _todo
    0.06
    %A
    0.06
    (log
    0.06
    licit
    0.06
    (author
    0.06
    handled
    0.06
    _factors
    0.06
    Act Density 0.030%

    No Known Activations