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

    Neuronpedia

    INDEX
    Explanations

    understanding the what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ng
    0.56
    kommen
    0.54
     інших
    0.52
    omeness
    0.52
    ၊
    0.51
     ފ
    0.50
    學生
    0.49
    onnaise
    0.49
     bạn
    0.48
    ri
    0.48
    POSITIVE LOGITS
    ר
    1.04
    ת
    0.79
    n
    0.72
    ad
    0.65
    น
    0.62
    یا
    0.61
    נ
    0.61
    ت
    0.60
    ה
    0.60
    ια
    0.56
    Act Density 1.996%

    No Known Activations