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

    Neuronpedia

    INDEX
    Explanations

    json output format

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    elift
    0.70
    ylab
    0.67
     कैश
    0.64
    酶
    0.63
     doss
    0.62
    ᱲ
    0.62
    タイル
    0.62
     loaders
    0.61
     enzimas
    0.61
     Oper
    0.61
    POSITIVE LOGITS
     captured
    0.59
     कैप
    0.58
     authenticated
    0.56
     ho
    0.54
     barb
    0.53
    競馬
    0.52
     यांचा
    0.52
     впечат
    0.51
     होतात
    0.50
     கொள்க
    0.50
    Act Density 0.091%

    No Known Activations