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

    Neuronpedia

    INDEX
    Explanations

    schema and code parsing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    foresaid
    0.40
    百分
    0.38
     चिल्
    0.37
    achery
    0.37
    應
    0.35
     وقت
    0.35
    嚜
    0.35
    عم
    0.35
     純正
    0.35
    应
    0.35
    POSITIVE LOGITS
     भले
    0.36
     ৩
    0.35
    ３
    0.34
     seven
    0.34
    3
    0.34
    ="#"
    0.33
    Lng
    0.33
     ۳
    0.33
     libsql
    0.33
     spécialistes
    0.33
    Act Density 0.003%

    No Known Activations