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

    Neuronpedia

    INDEX
    Explanations

    description to give

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ワイト
    0.45
    ദ്ധി
    0.43
    relax
    0.42
    behav
    0.41
    relaxation
    0.41
    beweg
    0.40
     relax
    0.39
    îne
    0.38
    StatusBadRequest
    0.38
    ﻻ
    0.38
    POSITIVE LOGITS
    ometry
    0.46
    phthalm
    0.44
     Teles
    0.42
     аспек
    0.42
     telescopes
    0.41
    व्यक्तित्व
    0.40
    ometer
    0.40
    उसके
    0.40
     estilo
    0.40
     मीटर
    0.40
    Act Density 0.001%

    No Known Activations