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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ين
    0.83
     സന്ത
    0.82
    ﻭ
    0.82
    wapV
    0.82
    ﺩ
    0.78
    Normdaten
    0.76
    regelen
    0.73
    BtnPanel
    0.72
    textColor
    0.71
    gesamt
    0.70
    POSITIVE LOGITS
     scum
    0.75
    3
    0.73
    2
    0.71
    עם
    0.66
    আই
    0.66
     Activision
    0.66
     Wellington
    0.65
     stycznia
    0.64
     loosened
    0.64
    4
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.