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

    Neuronpedia

    INDEX
    Explanations

    explaining concepts or rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    宾
    0.52
    DeviceCompliance
    0.45
    वणी
    0.44
    Calibration
    0.44
    enza
    0.44
    賓
    0.44
    路径
    0.41
    Marie
    0.40
    East
    0.40
    Kabhi
    0.40
    POSITIVE LOGITS
     disponibles
    0.54
     Ordinary
    0.53
     entrants
    0.53
     ordinary
    0.52
     unaffected
    0.51
     sweats
    0.50
     patents
    0.50
    !:
    0.50
     heats
    0.49
     available
    0.49
    Act Density 0.001%

    No Known Activations