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

    Neuronpedia

    INDEX
    Explanations

    number of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nogen
    0.83
     rid
    0.80
    та
    0.80
     حتی
    0.79
    lubridate
    0.79
    ynchronous
    0.77
    ﻐ
    0.77
    chetti
    0.77
    ಟರ್
    0.76
     mixing
    0.76
    POSITIVE LOGITS
    FormatException
    1.12
    odeon
    0.81
    ######
    0.79
    ጥር
    0.78
     हाथ
    0.78
     प्लेट
    0.77
    人的
    0.76
    external
    0.76
    dis
    0.76
     glyc
    0.75
    Act Density 0.250%

    No Known Activations