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

    Neuronpedia

    INDEX
    Explanations

    living

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    保证
    -0.08
     Publisher
    -0.07
    -0.07
     van
    -0.06
     Scheduler
    -0.06
    _segments
    -0.06
    _DEFAULT
    -0.06
    _camera
    -0.06
    _FAILED
    -0.06
    Beginning
    -0.06
    POSITIVE LOGITS
    _SIGN
    0.07
    rus
    0.07
     tog
    0.06
    -toolbar
    0.06
     uç
    0.06
    ListItem
    0.06
    _gold
    0.06
     TJ
    0.06
    (coeff
    0.06
     голов
    0.06
    Act Density 0.006%
    No Known Activations