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

    Neuronpedia

    INDEX
    Explanations

    abstract descriptive qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cute
    0.56
     cinco
    0.52
     Earrings
    0.51
     Datei
    0.50
     zwei
    0.49
     Horror
    0.48
     Photoshop
    0.48
     kiddos
    0.48
     kics
    0.48
     danni
    0.48
    POSITIVE LOGITS
     pervasive
    0.64
     enduring
    0.59
     demonstrable
    0.57
     unwavering
    0.56
     compelling
    0.55
     relentless
    0.55
     discernible
    0.54
     measurable
    0.53
     overarching
    0.51
     continually
    0.51
    Act Density 1.373%

    No Known Activations