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
    CENTER
    -0.07
     jednu
    -0.06
    adar
    -0.06
    vat
    -0.06
    _translate
    -0.06
     jt
    -0.06
    Reservation
    -0.06
    559
    -0.06
    _fold
    -0.06
    /movie
    -0.06
    POSITIVE LOGITS
     Slow
    0.06
    ी↵
    0.06
    ');↵↵↵
    0.06
    ">${
    0.06
     fellow
    0.06
     an
    0.06
     televis
    0.06
    .form
    0.06
     provincia
    0.06
     continuum
    0.06
    Act Density 0.033%

    No Known Activations