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

    Neuronpedia

    INDEX
    Explanations

    news articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     curses
    -0.07
    ncmp
    -0.06
     Mul
    -0.06
    _probs
    -0.06
     amour
    -0.06
    302
    -0.06
    .View
    -0.06
    ?p
    -0.06
     кому
    -0.06
     altru
    -0.06
    POSITIVE LOGITS
    チェ
    0.07
     setImage
    0.06
     MERCHANTABILITY
    0.06
     clientId
    0.06
    alaria
    0.06
     northeast
    0.06
    Requires
    0.06
     unemployed
    0.06
     flair
    0.06
     Kunst
    0.06
    Act Density 0.177%

    No Known Activations