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

    Neuronpedia

    INDEX
    Explanations

    code and punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Malcolm
    -0.06
    (padding
    -0.06
    -Disposition
    -0.06
    정보
    -0.06
    -wheel
    -0.06
     appending
    -0.06
     sotto
    -0.06
     Greatest
    -0.06
    .NEW
    -0.06
    +"
    -0.06
    POSITIVE LOGITS
    icester
    0.06
    DDR
    0.06
     advisable
    0.06
     corps
    0.06
    ังหว
    0.06
     région
    0.06
    rine
    0.06
     ดร
    0.06
     наказ
    0.06
     QDialog
    0.06
    Act Density 0.005%

    No Known Activations