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

    Neuronpedia

    INDEX
    Explanations

    public class or enum

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     गोपनीयता
    0.42
     privacidad
    0.41
    ueses
    0.41
    .):
    0.40
    သက်
    0.39
    anlı
    0.39
     logique
    0.39
     :=
    0.38
    隐私
    0.38
     privacidade
    0.38
    POSITIVE LOGITS
     sealed
    0.62
    enum
    0.57
     enum
    0.53
    sealed
    0.51
    封
    0.51
    interface
    0.49
     interface
    0.47
     sealer
    0.46
     sealing
    0.45
     seal
    0.45
    Act Density 0.004%

    No Known Activations