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
    }</
    -0.06
     بشر
    -0.06
     IRS
    -0.06
    ıy
    -0.06
     врач
    -0.06
     Tasmania
    -0.06
     Hits
    -0.06
     Toyota
    -0.06
    Detroit
    -0.06
     ف
    -0.06
    POSITIVE LOGITS
    시에
    0.07
     vn
    0.06
     rég
    0.06
    年に
    0.06
    .tools
    0.06
    ...,
    0.06
     MK
    0.06
     outer
    0.06
    .cell
    0.06
    (push
    0.06
    Act Density 0.121%

    No Known Activations