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

    Neuronpedia

    INDEX
    Explanations

    predict outbreaks or densely populated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lotions
    1.38
    פּ
    1.27
    ્ષ
    1.22
     accessori
    1.19
     Crafts
    1.15
     Antenna
    1.13
    tained
    1.13
     Regex
    1.10
    性
    1.10
     Puget
    1.08
    POSITIVE LOGITS
     gelap
    1.43
    mitglied
    1.30
    hoy
    1.26
     стрем
    1.16
    urando
    1.15
    紝
    1.14
    hspace
    1.14
    ﻳ
    1.13
    ය
    1.12
     diarias
    1.12
    Act Density 0.001%

    No Known Activations