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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    in
    1.02
    up
    1.01
    as
    0.85
    it
    0.85
     साथ
    0.84
    り
    0.78
    urring
    0.75
    term
    0.72
    ってください
    0.71
     öt
    0.70
    POSITIVE LOGITS
     unprepared
    0.76
    Shiny
    0.73
     Oiseaux
    0.72
     stunted
    0.72
    尺
    0.71
     vases
    0.71
    RMSE
    0.69
    如图
    0.69
    Pourquoi
    0.69
    RFID
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.