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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    rons
    -0.78
    Ô
    -0.77
    reon
    -0.74
    aimon
    -0.67
    lov
    -0.67
    zn
    -0.67
    ty
    -0.66
    Pos
    -0.64
     shedding
    -0.63
    asking
    -0.63
    POSITIVE LOGITS
     {:
    0.78
     cous
    0.73
     Digital
    0.72
     Murd
    0.69
    marine
    0.69
    emouth
    0.69
     Difficulty
    0.69
     Annotations
    0.67
     Aires
    0.66
     Dynamo
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.