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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مشک
    -0.07
    abyrinth
    -0.07
    flo
    -0.07
    Svg
    -0.07
     Malik
    -0.07
    estone
    -0.07
     mercenaries
    -0.07
    jee
    -0.07
    .dec
    -0.07
    glomer
    -0.07
    POSITIVE LOGITS
     bird
    0.06
     Out
    0.06
     Civic
    0.06
     Word
    0.05
     Read
    0.05
    CHASE
    0.05
    _years
    0.05
     Weld
    0.05
     prominence
    0.05
    ;j
    0.05
    Act Density 0.018%

    No Known Activations