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

    Neuronpedia

    INDEX
    Explanations

    section titles and key terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Jähr
    0.60
     conness
    0.51
     January
    0.51
     wurde
    0.51
     daños
    0.50
     souligne
    0.50
     doanh
    0.50
     იყ
    0.50
     янва
    0.48
     similaires
    0.48
    POSITIVE LOGITS
     the
    0.59
    the
    0.53
    ordinal
    0.48
    otonic
    0.47
     all
    0.46
    ￠
    0.46
    an
    0.44
    به
    0.44
    。",
    0.43
    uot
    0.43
    Act Density 0.125%

    No Known Activations