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

    Neuronpedia

    INDEX
    Explanations

    US amendment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ფ
    0.51
    罣
    0.45
     salariés
    0.45
    تر
    0.44
    τι
    0.44
     épouse
    0.44
    ائن
    0.44
    ود
    0.43
    形容
    0.42
    魉
    0.42
    POSITIVE LOGITS
    -
    0.46
    etric
    0.46
     ಮಾಡಿ
    0.44
    roy
    0.40
    iew
    0.39
    ament
    0.39
     means
    0.39
     நாள்
    0.39
     Итак
    0.39
     bounces
    0.39
    Act Density 0.004%

    No Known Activations