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

    Neuronpedia

    INDEX
    Explanations

    Acronyms and named entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    c
    0.63
    慎
    0.54
     Chủ
    0.53
     अशुभ
    0.53
     Hacks
    0.50
    发展
    0.49
     المناطق
    0.49
     провод
    0.48
     हत्याकांड
    0.48
     unfortunate
    0.48
    POSITIVE LOGITS
    س
    0.69
    ش
    0.64
     escalera
    0.62
     jaunâtre
    0.60
    شون
    0.59
    Clo
    0.59
    סי
    0.57
    стые
    0.57
    טי
    0.56
    ordre
    0.55
    Act Density 0.031%

    No Known Activations