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

    Neuronpedia

    INDEX
    Explanations

    conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bingo
    -0.07
     Emperor
    -0.07
     UNKNOWN
    -0.07
    _va
    -0.07
     Strap
    -0.06
    _math
    -0.06
    roof
    -0.06
     Musical
    -0.06
     softball
    -0.06
     vers
    -0.06
    POSITIVE LOGITS
    атив
    0.07
    =R
    0.07
    toHaveBeenCalled
    0.07
     فرآ
    0.06
    983
    0.06
    retim
    0.06
    .repo
    0.06
    ADDRESS
    0.06
    邮
    0.06
     getattr
    0.06
    Act Density 0.093%

    No Known Activations