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

    Neuronpedia

    INDEX
    Explanations

    Industries and corporations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     который
    0.56
    oitte
    0.49
     অনুষ্ঠান
    0.48
     କ
    0.48
    ተት
    0.48
    鈳
    0.48
     जेटली
    0.48
    ো
    0.46
     我們
    0.45
    𝙤
    0.45
    POSITIVE LOGITS
    0
    0.88
    ppure
    0.61
    ;
    0.60
    x
    0.59
    پ
    0.59
    """
    0.57
     about
    0.54
    <h3>
    0.54
    )$
    0.52
    ૦
    0.52
    Act Density 0.019%

    No Known Activations