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

    Neuronpedia

    INDEX
    Explanations

    HTML table structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ௐ
    1.02
    ﺲ
    1.02
    ])
    1.02
    できる
    0.99
    時に
    0.98
    шем
    0.98
    ńst
    0.97
     that
    0.97
     deducting
    0.89
    ﺶ
    0.89
    POSITIVE LOGITS
    in
    1.86
    ul
    1.66
    im
    1.63
    n
    1.63
    un
    1.39
    w
    1.37
    ↵
    1.36
    -
    1.34
    te
    1.30
    ub
    1.22
    Act Density 0.000%

    No Known Activations