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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ம்மா
    0.76
     душу
    0.74
     actionBar
    0.72
     ৯
    0.72
     containing
    0.72
     ১০
    0.71
     மழை
    0.69
    十一
    0.69
    inch
    0.68
     nine
    0.68
    POSITIVE LOGITS
    éroport
    0.72
     raro
    0.68
     derivable
    0.65
    ugi
    0.63
     независи
    0.62
    `](
    0.61
    战
    0.61
    uca
    0.61
    लोकन
    0.61
    newswire
    0.61
    Act Density 0.009%

    No Known Activations