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

    Neuronpedia

    INDEX
    Explanations

    security

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    及
    -0.07
    _timer
    -0.06
    \\
    -0.06
    370
    -0.06
     парт
    -0.06
    Owned
    -0.06
    owski
    -0.06
     curated
    -0.06
    uyo
    -0.06
     इक
    -0.06
    POSITIVE LOGITS
    #Region
    0.07
     strán
    0.07
    érc
    0.06
    iflower
    0.06
    .Errors
    0.06
    gow
    0.06
     Bd
    0.06
     beware
    0.06
     santé
    0.06
     Mineral
    0.06
    Act Density 0.026%

    No Known Activations