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

    Neuronpedia

    INDEX
    Explanations

    Capability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    placing
    -0.07
     위
    -0.06
     Positioned
    -0.06
     کی
    -0.06
     fık
    -0.06
     csv
    -0.06
     Basic
    -0.06
     translations
    -0.06
    643
    -0.06
     sincerity
    -0.06
    POSITIVE LOGITS
     apparently
    0.07
    .SaveChangesAsync
    0.07
    idine
    0.06
    hen
    0.06
     coerce
    0.06
     stabilize
    0.06
    fork
    0.06
     köln
    0.06
     Boulder
    0.06
     образом
    0.06
    Act Density 0.154%

    No Known Activations