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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Languages
    -0.07
    课程
    -0.07
    .reason
    -0.07
    _python
    -0.07
    _delay
    -0.07
     TIM
    -0.07
    辅导员
    -0.07
     licenses
    -0.07
    してください
    -0.07
    appid
    -0.07
    POSITIVE LOGITS
     hasn
    0.08
    anguard
    0.08
     harb
    0.07
    Describe
    0.07
    存量
    0.07
     handleClose
    0.06
    חקירה
    0.06
     rise
    0.06
     prer
    0.06
     priorit
    0.06
    Act Density 0.122%

    No Known Activations