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

    Neuronpedia

    INDEX
    Explanations

    playing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     や
    -0.07
    кость
    -0.07
    .source
    -0.07
     Factor
    -0.06
     Yosh
    -0.06
     skiing
    -0.06
     responseBody
    -0.06
     guardians
    -0.06
     Серг
    -0.06
    Typed
    -0.06
    POSITIVE LOGITS
    cul
    0.06
    performance
    0.06
    ilendir
    0.06
     Speed
    0.06
    、二
    0.06
    _Static
    0.06
     unb
    0.06
    (net
    0.05
     vòng
    0.05
     eleven
    0.05
    Act Density 0.013%

    No Known Activations