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

    Neuronpedia

    INDEX
    Explanations

    ending something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     جسم
    0.61
    risch
    0.60
    kin
    0.59
    का
    0.59
    enn
    0.59
    ott
    0.58
    raya
    0.58
    uit
    0.57
    raft
    0.57
    iv
    0.56
    POSITIVE LOGITS
    قبل
    0.63
    ق
    0.61
    ש
    0.61
    س
    0.61
    ﻻ
    0.59
    för
    0.59
     fér
    0.59
     Basta
    0.59
     Gewalt
    0.59
    峇
    0.57
    Act Density 0.007%

    No Known Activations