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

    Neuronpedia

    INDEX
    Explanations

    series, sequence, iterator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    irar
    0.49
    k
    0.48
    ⑸
    0.47
    kten
    0.46
    kst
    0.46
    kta
    0.46
    stri
    0.46
     сво
    0.45
    ransition
    0.44
    let
    0.44
    POSITIVE LOGITS
     Q
    0.50
     phun
    0.49
     Ř
    0.48
     S
    0.48
     B
    0.47
     Delt
    0.46
     genug
    0.45
     Airlines
    0.45
     Beide
    0.45
     E
    0.45
    Act Density 0.002%

    No Known Activations