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

    Neuronpedia

    INDEX
    Explanations

    which of the following options or statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ുകളും
    0.74
    在那里
    0.69
    Whatever
    0.68
    ികളും
    0.67
     whatever
    0.67
     Whatever
    0.65
    their
    0.63
    巨大
    0.62
    ंदी
    0.61
    だけの
    0.61
    POSITIVE LOGITS
     statements
    1.93
     statement
    1.85
     Statements
    1.57
     Statement
    1.51
    statements
    1.50
    statement
    1.47
     pernyataan
    1.41
    Statement
    1.31
    Statements
    1.30
     enunciado
    1.29
    Act Density 0.211%

    No Known Activations