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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ww
    -0.07
     ем
    -0.07
    Queue
    -0.07
     обо
    -0.06
    .bel
    -0.06
    _IRQn
    -0.06
     الأم
    -0.06
    .result
    -0.06
    ?;↵
    -0.06
     injunction
    -0.06
    POSITIVE LOGITS
     結
    0.06
    _plots
    0.06
    ovice
    0.06
    _pickle
    0.06
     Stud
    0.06
    (gray
    0.06
     ACCEPT
    0.06
     shock
    0.06
    (layers
    0.05
    /testing
    0.05
    Act Density 0.019%

    No Known Activations