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

    Neuronpedia

    INDEX
    Explanations

    miscellaneous words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    1.77
    ’
    1.48
    }'
    0.79
    ścia
    0.71
     chatt
    0.71
    ()'
    0.68
    $'
    0.67
     Tann
    0.67
    '/
    0.66
    '...
    0.65
    POSITIVE LOGITS
    ne
    0.82
     २५
    0.82
     ৫৫
    0.82
    l
    0.82
    không
    0.79
    cic
    0.79
    не
    0.78
     १७
    0.78
    the
    0.77
     Dont
    0.77
    Act Density 0.000%

    No Known Activations