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

    Neuronpedia

    INDEX
    Explanations

    books, movies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pitches
    -0.07
    lay
    -0.07
     cap
    -0.07
     amounted
    -0.06
    LAY
    -0.06
     confirm
    -0.06
    ogi
    -0.06
    (assigns
    -0.06
    олн
    -0.06
    זר
    -0.06
    POSITIVE LOGITS
    .putString
    0.08
    .Feature
    0.07
     ander
    0.07
    .onError
    0.07
     curious
    0.07
     Hispanics
    0.07
    导弹
    0.06
    新规
    0.06
    _BOUNDS
    0.06
     Bund
    0.06
    Act Density 0.054%

    No Known Activations