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

    Neuronpedia

    INDEX
    Explanations

    return (

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ق
    1.61
    ا
    1.60
    '.
    1.51
    أ
    1.46
    ה
    1.45
    ற்போது
    1.42
     угла
    1.39
    جیت
    1.37
    ەك
    1.37
     niche
    1.36
    POSITIVE LOGITS
    ted
    1.94
    ième
    1.91
    teenth
    1.73
    te
    1.64
    stwo
    1.63
     hammock
    1.62
    ließen
    1.56
    tect
    1.55
    जापुर
    1.54
    raj
    1.54
    Act Density 0.009%

    No Known Activations