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

    Neuronpedia

    INDEX
    Explanations

    table features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     comput
    0.47
     entrop
    0.43
     dữ
    0.41
     całym
    0.41
     fusión
    0.40
     cálculo
    0.39
     necesaria
    0.39
     nodal
    0.39
     totalling
    0.39
     travers
    0.39
    POSITIVE LOGITS
     불구하고
    0.35
    yme
    0.32
    yaratan
    0.31
    ariat
    0.30
    テッド
    0.30
     обе
    0.30
     tetahi
    0.30
    哼
    0.30
    inch
    0.29
     egli
    0.29
    Act Density 0.012%

    No Known Activations