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

    Neuronpedia

    INDEX
    Explanations

    technical documentation review

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NAL
    0.82
    ступ
    0.80
    ки
    0.75
    earing
    0.74
    ه
    0.74
    লের
    0.71
    se
    0.71
    ar
    0.70
    то
    0.68
    ج
    0.67
    POSITIVE LOGITS
     tenemos
    0.84
     HDD
    0.82
     подобрать
    0.82
     бонусу
    0.82
     FTIR
    0.80
     monomer
    0.79
     pequ
    0.79
     इनकम
    0.79
     pangkat
    0.78
     americanos
    0.77
    Act Density 0.000%

    No Known Activations