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

    Neuronpedia

    INDEX
    Explanations

    stars are likely

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     করিয়৷
    0.51
    า
    0.47
    ありません
    0.45
     सूर्
    0.44
     StringSet
    0.43
    inę
    0.43
     गरजेचे
    0.43
    <unused2012>
    0.42
     হুইয়
    0.41
    爣
    0.41
    POSITIVE LOGITS
     traumas
    0.54
     scrapes
    0.51
     sépt
    0.48
     pocas
    0.48
     EBITDA
    0.46
     emissions
    0.46
     cubrir
    0.46
     concedes
    0.45
     emisiones
    0.45
     medias
    0.45
    Act Density 0.001%

    No Known Activations