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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.92
    ascus
    -0.81
     independ
    -0.77
     involuntary
    -0.75
    emaker
    -0.75
    apan
    -0.73
    oing
    -0.73
     estab
    -0.72
    icker
    -0.72
     hourly
    -0.71
    POSITIVE LOGITS
     Unfortunately
    0.82
     Granted
    0.81
     Places
    0.80
     Sadly
    0.78
     Turns
    0.78
     Suit
    0.77
     Grants
    0.77
     Spaces
    0.75
     Belief
    0.75
     Conversion
    0.75
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.