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

    Neuronpedia

    INDEX
    Explanations

    information entries definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     infin
    0.46
     superconducting
    0.46
    pgamma
    0.43
    کنند
    0.43
    INFINITY
    0.43
    씀
    0.43
     offices
    0.43
     infinito
    0.43
     ニュー
    0.42
    qk
    0.42
    POSITIVE LOGITS
    ruar
    0.49
     be
    0.48
    Sab
    0.46
     има
    0.45
    eous
    0.45
    För
    0.44
    erade
    0.44
    とされる
    0.43
    шинство
    0.43
    Durante
    0.43
    Act Density 0.002%

    No Known Activations