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

    Neuronpedia

    INDEX
    Explanations

    stopped

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     घोड़
    0.29
     cười
    0.27
    اداسی
    0.27
    丳
    0.26
    0.25
     دیوار
    0.25
    зво
    0.25
    swiper
    0.25
     പ്രതിഷേധ
    0.25
     الجلد
    0.24
    POSITIVE LOGITS
     acts
    0.28
     wastes
    0.27
     tetap
    0.27
     suspicions
    0.26
     stipulations
    0.26
     tentativas
    0.26
    gaben
    0.25
     withheld
    0.24
    IVA
    0.24
     arrangements
    0.24
    Act Density 0.006%

    No Known Activations