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

    Neuronpedia

    INDEX
    Explanations

    context and concise explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ل
    1.48
    で
    1.32
    \"\
    1.31
    /-}$
    1.29
    8
    1.28
    다는
    1.26
    ো
    1.26
    4
    1.26
    ется
    1.24
    5
    1.23
    POSITIVE LOGITS
    gt
    1.81
    y
    1.77
    gs
    1.67
    le
    1.66
    ga
    1.66
    ine
    1.61
    nl
    1.54
    ט
    1.53
    et
    1.52
    ك
    1.51
    Act Density 0.254%

    No Known Activations