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

    Neuronpedia

    INDEX
    Explanations

    stehen für or put

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    umping
    0.48
    忤
    0.46
    ^+,
    0.45
    ByMerging
    0.45
    മിഷ
    0.45
    서를
    0.44
    fireFlower
    0.44
    FEDERAL
    0.44
     கூறு
    0.44
    JsonPart
    0.43
    POSITIVE LOGITS
     on
    0.56
     del
    0.48
     rediscover
    0.47
     clearance
    0.44
     put
    0.43
     Haz
    0.43
     performance
    0.41
     Are
    0.41
     midwife
    0.40
     festival
    0.40
    Act Density 0.001%

    No Known Activations