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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ")(
    0.52
    (";
    0.50
     Einstellungen
    0.50
    '][
    0.50
    💂
    0.49
    FlashValue
    0.49
     значения
    0.48
    IdleSync
    0.47
    <unused2140>
    0.47
     Sprachen
    0.47
    POSITIVE LOGITS
     beat
    0.60
     revival
    0.51
     cooling
    0.51
     doubled
    0.49
     civil
    0.49
     clock
    0.49
     game
    0.48
     refund
    0.48
     carpet
    0.47
     be
    0.47
    Act Density 0.000%

    No Known Activations