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

    Neuronpedia

    INDEX
    Explanations

    no

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    תקש
    -0.07
    ходить
    -0.07
    봊
    -0.07
     BlackBerry
    -0.07
     Press
    -0.07
    跄
    -0.07
    师范大学
    -0.06
    ጦ
    -0.06
    etur
    -0.06
     Bundy
    -0.06
    POSITIVE LOGITS
     empt
    0.08
     sliding
    0.08
     ());↵
    0.07
     grading
    0.07
    实木
    0.07
    自营
    0.07
    _PROD
    0.07
     optim
    0.07
    إيم
    0.06
    _states
    0.06
    Act Density 0.000%

    No Known Activations