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

    Neuronpedia

    INDEX
    Explanations

    questions, reactions, advantage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trazendo
    0.45
    muje
    0.44
     excellence
    0.44
     excelencia
    0.44
    दृ
    0.44
    larında
    0.43
    resultados
    0.43
    вичайно
    0.43
    utacji
    0.43
    が出来
    0.43
    POSITIVE LOGITS
     with
    0.71
     to
    0.64
     on
    0.63
     for
    0.55
     from
    0.53
     على
    0.52
     với
    0.51
    with
    0.50
     by
    0.47
     onto
    0.46
    Act Density 0.000%

    No Known Activations