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

    Neuronpedia

    INDEX
    Explanations

    numbers and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Otro
    1.07
    𝖊
    1.03
    렀
    1.02
     värld
    0.96
     искусства
    0.95
    Ⅽ
    0.91
     Дэ
    0.86
     свидетель
    0.84
     começ
    0.84
     está
    0.84
    POSITIVE LOGITS
    ians
    0.88
    ança
    0.79
     gain
    0.79
    abilities
    0.78
    anian
    0.78
    াভাব
    0.77
     chances
    0.75
    icking
    0.74
    isco
    0.74
     large
    0.74
    Act Density 0.000%

    No Known Activations