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
    plot
    -0.07
     withd
    -0.06
     corpo
    -0.06
     comerc
    -0.06
     relig
    -0.06
     selects
    -0.06
     yere
    -0.06
    cının
    -0.06
     otro
    -0.06
     constant
    -0.06
    POSITIVE LOGITS
    NON
    0.07
    _NEXT
    0.07
    Adobe
    0.07
     porn
    0.06
    jejer
    0.06
     anlaş
    0.06
     Korean
    0.06
    ол
    0.06
    .product
    0.06
    jylland
    0.06
    Act Density 0.002%

    No Known Activations