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

    Neuronpedia

    INDEX
    Explanations

    Acronyms and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    이지만
    0.44
     glaring
    0.41
    이었다
    0.38
     crucifixion
    0.38
    ও
    0.38
    도
    0.37
     countertop
    0.37
     religieux
    0.37
     Zumba
    0.36
    েরও
    0.35
    POSITIVE LOGITS
    the
    0.71
    1
    0.58
    t
    0.55
    ка
    0.51
    i
    0.50
     at
    0.49
    ד
    0.47
    a
    0.45
    to
    0.44
    CE
    0.44
    Act Density 0.155%

    No Known Activations