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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Bah
    -0.07
     Gow
    -0.07
    Requests
    -0.06
    恨
    -0.06
    (W
    -0.06
    )L
    -0.06
    setw
    -0.06
    Various
    -0.06
    вест
    -0.06
     О
    -0.06
    POSITIVE LOGITS
    _certificate
    0.07
     maç
    0.06
    ційно
    0.06
     vấn
    0.06
     onBackPressed
    0.06
    /apps
    0.06
     разм
    0.06
     Plzeň
    0.06
     Bedford
    0.06
    _log
    0.06
    Act Density 0.000%

    No Known Activations