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

    Neuronpedia

    INDEX
    Explanations

    abbreviations or code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ―――――
    -1.86
     myſelf
    -1.78
     Efq
    -1.77
     itſelf
    -1.66
     Monfieur
    -1.59
     doubtnut
    -1.59
     iſt
    -1.55
     Theſe
    -1.55
     Jefus
    -1.54
     ་་
    -1.52
    POSITIVE LOGITS
     nationaux
    0.85
    <eos>
    0.85
     actuels
    0.83
     réguli
    0.81
     pauvres
    0.80
     actuelles
    0.79
     juridiques
    0.79
     spéciaux
    0.77
     sanitaires
    0.76
     fédé
    0.76
    Act Density 0.151%

    No Known Activations