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

    Neuronpedia

    INDEX
    Explanations

    defender

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -',
    -0.07
    ус
    -0.07
    :::::::::::::::
    -0.07
     alf
    -0.07
     Papa
    -0.06
     rub
    -0.06
    Dash
    -0.06
    .playlist
    -0.06
    rics
    -0.06
     Cornell
    -0.06
    POSITIVE LOGITS
    /QĐ
    0.07
     defender
    0.07
    _ANT
    0.06
    `
↵
    0.06
     مسلمان
    0.06
    timer
    0.06
    "));↵↵
    0.06
    _gem
    0.06
    .DateTime
    0.06
    生き
    0.05
    Act Density 0.002%

    No Known Activations