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

    Neuronpedia

    INDEX
    Explanations

    academic journals and studies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    畤
    0.40
    旪
    0.38
    Guarantee
    0.38
    ливо
    0.37
    态
    0.36
    úz
    0.36
    峙
    0.36
    孚
    0.36
    啞
    0.36
    นด์
    0.35
    POSITIVE LOGITS
    늦
    0.41
     tartar
    0.40
     potenti
    0.39
     fluctuation
    0.39
     Kenyans
    0.39
    emorrh
    0.38
     CYAN
    0.37
     acceler
    0.37
     distal
    0.37
     pathologic
    0.37
    Act Density 0.002%

    No Known Activations