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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    getX
    -0.07
    กำล
    -0.07
     Armor
    -0.06
    وره
    -0.06
    ryption
    -0.06
    (identity
    -0.06
    반
    -0.06
    .setStroke
    -0.06
     право
    -0.06
    _clause
    -0.06
    POSITIVE LOGITS
     Elliott
    0.07
     excessive
    0.06
     simulate
    0.06
     retains
    0.06
     olmadı
    0.06
     elektronik
    0.06
     Jag
    0.06
    geç
    0.06
     emotional
    0.06
    /kg
    0.06
    Act Density 0.011%

    No Known Activations