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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Scientific
    -0.08
    ,H
    -0.07
    Bruce
    -0.07
     Guid
    -0.07
    loom
    -0.07
    芜
    -0.07
    Old
    -0.07
     Roof
    -0.07
    天空
    -0.06
    -blue
    -0.06
    POSITIVE LOGITS
    灾区
    0.07
     עצ
    0.07
    icator
    0.07
    _invoke
    0.07
    (disposing
    0.07
    .Normal
    0.07
     genitals
    0.07
     qreal
    0.06
     vezes
    0.06
     deputies
    0.06
    Act Density 0.004%

    No Known Activations