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

    Neuronpedia

    INDEX
    Explanations

    monetary values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     organisms
    0.46
     adrenergic
    0.43
     language
    0.42
     isoforms
    0.41
     Debye
    0.41
     Brownian
    0.40
     Punkt
    0.40
     initialized
    0.39
     Boltzmann
    0.39
     punctuation
    0.39
    POSITIVE LOGITS
    -$
    1.11
    dollars
    0.96
     ($
    0.95
     dollars
    0.95
    /$
    0.95
    ($
    0.93
     dólares
    0.91
     долларов
    0.91
    =$
    0.89
     dollari
    0.87
    Act Density 0.042%

    No Known Activations