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

    Neuronpedia

    INDEX
    Explanations

    private or public

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    instance
    0.54
    static
    0.52
     instance
    0.49
     static
    0.48
    extension
    0.47
     Instance
    0.46
     STATIC
    0.46
    extensions
    0.45
    INSTANCE
    0.45
     extension
    0.45
    POSITIVE LOGITS
     privato
    0.54
     private
    0.49
     privately
    0.49
     seals
    0.48
    Private
    0.48
     privata
    0.45
     privée
    0.44
    私
    0.44
     prywat
    0.44
     privati
    0.44
    Act Density 0.002%

    No Known Activations