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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     NX
    -0.63
     GOODMAN
    -0.62
     Sounds
    -0.62
     Monarch
    -0.62
     RX
    -0.61
     Cerberus
    -0.61
    rador
    -0.61
     sacrific
    -0.60
     indic
    -0.59
     Nano
    -0.58
    POSITIVE LOGITS
    elf
    0.74
    Bound
    0.72
    gging
    0.69
    DO
    0.66
    heed
    0.66
    Redd
    0.65
    Blake
    0.63
    perty
    0.63
    bound
    0.63
    EEK
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.