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

    Neuronpedia

    INDEX
    Explanations

    indexing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     previsão
    0.37
     conve
    0.36
     pitanje
    0.35
    ുവെ
    0.35
     उद्धव
    0.34
    casted
    0.34
    appi
    0.34
     McColl
    0.34
    owała
    0.33
    ್ರ
    0.33
    POSITIVE LOGITS
     Index
    0.63
     index
    0.60
     индекс
    0.57
    索引
    0.55
    INDEX
    0.55
    index
    0.53
    Index
    0.52
     indexing
    0.52
     индек
    0.50
     INDEX
    0.49
    Act Density 0.000%

    No Known Activations