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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions and specific contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ิ
    0.55
     führt
    0.52
    τικά
    0.50
     ohne
    0.48
     handyman
    0.48
    ών
    0.47
     daydream
    0.47
    ické
    0.46
    క్షి
    0.46
     Zacks
    0.46
    POSITIVE LOGITS
    ankind
    0.44
     SEQU
    0.44
    มัน
    0.43
    طا
    0.41
    Æ
    0.40
    ಢ
    0.40
     ග
    0.39
    tuples
    0.39
    Ɛ
    0.39
     fifo
    0.38
    Act Density 0.001%

    No Known Activations