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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ವೇಂದ್ರ
    0.59
    ฯ
    0.57
     ܀
    0.56
    🏛
    0.55
     hampers
    0.55
     जाहिर
    0.54
    সন্
    0.54
     audiov
    0.53
     коопера
    0.53
     gsi
    0.52
    POSITIVE LOGITS
    5
    0.64
    2
    0.59
    4
    0.59
    1
    0.56
    3
    0.55
    8
    0.52
    0
    0.49
    ⽤
    0.49
    A
    0.47
    9
    0.47
    Act Density 0.007%

    No Known Activations