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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    派遣
    -0.08
     GitHub
    -0.07
     awarded
    -0.07
    hammad
    -0.07
    Miss
    -0.07
    舷
    -0.07
    inde
    -0.07
    реш
    -0.07
     quizzes
    -0.07
     Through
    -0.07
    POSITIVE LOGITS
    'util
    0.09
     לוקח
    0.08
    Console
    0.08
    服務或
    0.07
     התורה
    0.07
    خدام
    0.06
    _listen
    0.06
    _velocity
    0.06
    _PLUS
    0.06
     çeşit
    0.06
    Act Density 0.001%

    No Known Activations