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

    Neuronpedia

    INDEX
    Explanations

    Security

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -ID
    -0.07
     centroid
    -0.06
    лаг
    -0.06
    erb
    -0.06
    寻
    -0.06
    бира
    -0.06
    oron
    -0.06
    unft
    -0.06
    /sl
    -0.06
    Ark
    -0.06
    POSITIVE LOGITS
    Resize
    0.06
     Undert
    0.06
     chaque
    0.06
     tragedies
    0.06
    ственной
    0.06
     undert
    0.06
    (last
    0.06
     Bobby
    0.06
     "-//
    0.06
     Patio
    0.06
    Act Density 0.002%

    No Known Activations