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

    Neuronpedia

    INDEX
    Explanations

    balsamic reduction and damsels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    exual
    0.44
     comparative
    0.43
    ozu
    0.42
    ters
    0.41
     βα
    0.39
     сравни
    0.38
     Comparative
    0.38
    oxal
    0.37
    cu
    0.37
     StringVar
    0.36
    POSITIVE LOGITS
    ächlich
    0.46
    ु
    0.38
    els
    0.38
    ELS
    0.38
    elm
    0.37
    ัน
    0.36
    льский
    0.36
    ಳೆಯ
    0.36
     سننے
    0.36
    ulate
    0.35
    Act Density 0.012%

    No Known Activations