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

    Neuronpedia

    INDEX
    Explanations

    ISO standards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ї
    0.79
    いろいろ
    0.76
    in
    0.75
    いろんな
    0.75
    จะ
    0.75
    ளும்
    0.75
    на
    0.74
    ,
    0.73
    の使用
    0.73
    ﺔ
    0.73
    POSITIVE LOGITS
    de
    0.96
    ،
    0.90
    ан
    0.89
    0
    0.87
    ir
    0.86
     ISO
    0.84
    ISO
    0.83
    、
    0.81
    ailing
    0.80
    ao
    0.79
    Act Density 0.006%

    No Known Activations