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

    Neuronpedia

    INDEX
    Explanations

    Arm followed by common suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    แจ้ง
    0.97
     swamps
    0.94
    clude
    0.92
    avni
    0.90
    וס
    0.90
     Союз
    0.90
    cludes
    0.89
    েবের
    0.89
    raph
    0.88
    breadcrumbs
    0.87
    POSITIVE LOGITS
    adillo
    1.58
    chair
    1.41
    pits
    1.41
    chairs
    1.40
    pit
    1.36
    ageddon
    1.34
    istice
    1.30
    膀
    1.20
    ेल
    1.17
    チュア
    1.14
    Act Density 0.057%

    No Known Activations