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

    Neuronpedia

    INDEX
    Explanations

    listing items with 'and'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    一个
    1.10
    :
    1.08
    er
    1.06
    is
    1.01
     Both
    0.97
    !
    0.96
    Both
    0.96
    '
    0.95
    이
    0.94
    (
    0.94
    POSITIVE LOGITS
     sebagainya
    1.38
     hatta
    1.37
     soprattutto
    1.36
     lainnya
    1.31
    ስቃ
    1.31
     whatnot
    1.31
    enteuer
    1.26
     senza
    1.22
     bahkan
    1.21
     consigui
    1.20
    Act Density 0.126%

    No Known Activations