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

    Neuronpedia

    INDEX
    Explanations

    standardization and policies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    emente
    -0.07
    ESCO
    -0.07
     advertisements
    -0.07
     Ukraj
    -0.07
     metric
    -0.06
    adores
    -0.06
    lica
    -0.06
    โปร
    -0.06
    px
    -0.06
     equation
    -0.06
    POSITIVE LOGITS
    (remove
    0.07
    orsch
    0.07
    .structure
    0.06
    [np
    0.06
    활동
    0.06
    ={`/
    0.06
     vibes
    0.06
     insanın
    0.06
     негатив
    0.06
    Flo
    0.06
    Act Density 0.150%

    No Known Activations