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

    Neuronpedia

    INDEX
    Explanations

    button

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dynasty
    -0.07
    Tom
    -0.07
    Loss
    -0.07
    Equality
    -0.06
     Kor
    -0.06
    電
    -0.06
     ağır
    -0.06
     province
    -0.06
    来た
    -0.06
    公司
    -0.06
    POSITIVE LOGITS
    USE
    0.07
     trúc
    0.06
     eigen
    0.06
    (term
    0.06
     buttons
    0.06
     button
    0.06
    using
    0.06
     gotten
    0.06
     мож
    0.06
    itness
    0.06
    Act Density 0.005%

    No Known Activations