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

    Neuronpedia

    INDEX
    Explanations

    dates and specific items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    гли
    0.73
    Ah
    0.67
    פ
    0.66
    گ
    0.66
    д
    0.66
    ת
    0.66
     but
    0.64
     کیفیت
    0.63
    ט
    0.62
    تف
    0.61
    POSITIVE LOGITS
     incênd
    0.97
     resumo
    0.96
     cabelos
    0.96
     gestão
    0.94
    рый
    0.93
     вашей
    0.89
     endereço
    0.89
     escolas
    0.89
     crianças
    0.88
     alterações
    0.88
    Act Density 0.000%

    No Known Activations