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

    Neuronpedia

    INDEX
    Explanations

    resource name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eighty
    0.41
     accurate
    0.40
     \$
    0.39
     计算
    0.39
    āo
    0.39
    ไอ
    0.38
     oldest
    0.38
     Abby
    0.38
     Ix
    0.38
     sixty
    0.38
    POSITIVE LOGITS
    اف
    0.43
    حد
    0.39
    parad
    0.38
    رج
    0.38
     восста
    0.38
    restore
    0.37
     cenderung
    0.37
    બા
    0.37
    fir
    0.36
    ང
    0.36
    Act Density 0.000%

    No Known Activations