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

    Neuronpedia

    INDEX
    Explanations

    leads

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ضان
    -0.07
     mouseY
    -0.07
     cush
    -0.06
    く
    -0.06
    /english
    -0.06
    .left
    -0.06
    asd
    -0.06
     Institutional
    -0.06
    lamaya
    -0.06
     DatabaseReference
    -0.06
    POSITIVE LOGITS
     Comic
    0.07
    State
    0.06
     ACS
    0.06
     write
    0.06
     dependence
    0.06
    上海
    0.06
     geral
    0.06
    comma
    0.06
     commuting
    0.06
    ULT
    0.06
    Act Density 0.009%

    No Known Activations