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

    Neuronpedia

    INDEX
    Explanations

    training completion dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pozn
    0.40
    蛾
    0.40
    zna
    0.40
     Caus
    0.39
    茸
    0.39
    zos
    0.38
    ysel
    0.37
    ဳ
    0.37
    igita
    0.37
    camb
    0.37
    POSITIVE LOGITS
     backgrounds
    0.41
    foregroundView
    0.40
     словами
    0.40
    言葉
    0.39
     배경
    0.38
     চূড়ান্ত
    0.38
     electronic
    0.38
     ча
    0.38
     noisy
    0.38
     चैट
    0.37
    Act Density 0.004%

    No Known Activations