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

    Neuronpedia

    INDEX
    Explanations

    Expertise and Understanding

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     doing
    -0.08
     gchar
    -0.07
    _DRV
    -0.07
    .dropout
    -0.07
    _Order
    -0.07
    党组书记
    -0.07
    Toyota
    -0.07
     Longer
    -0.07
    ואב
    -0.07
    _colors
    -0.07
    POSITIVE LOGITS
    Blocked
    0.07
     warranted
    0.06
    bonus
    0.06
    zones
    0.06
    lines
    0.06
    '}
    0.06
    LAND
    0.06
    الياب
    0.06
    分流
    0.06
    (block
    0.06
    Act Density 0.020%

    No Known Activations