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

    Neuronpedia

    INDEX
    Explanations

    override string

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     void
    0.71
    void
    0.68
     over
    0.59
    def
    0.57
     def
    0.57
     private
    0.54
    Private
    0.53
    private
    0.50
     Private
    0.49
     voids
    0.45
    POSITIVE LOGITS
    ILTON
    0.46
    㧕
    0.42
    IMIENTO
    0.39
     harvested
    0.39
     capacités
    0.39
    俢
    0.39
     स्कूलों
    0.39
    immon
    0.39
     hinaus
    0.38
    ESOME
    0.38
    Act Density 0.001%

    No Known Activations