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

    Neuronpedia

    INDEX
    Explanations

    units of measure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kin
    -0.60
    tage
    -0.54
    ształ
    -0.54
     enfans
    -0.53
    зопас
    -0.53
     élas
    -0.53
    AccessorTable
    -0.51
    mtrl
    -0.50
     démocr
    -0.50
     normaux
    -0.50
    POSITIVE LOGITS
    WebVitals
    0.81
    CloseOperation
    0.79
     للمعارف
    0.77
    ’
    0.76
    '
    0.75
    IBOutlet
    0.64
    EndContext
    0.60
    rungsseite
    0.59
    WindowConstants
    0.59
    ]))
    0.56
    Act Density 0.309%

    No Known Activations