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

    Neuronpedia

    INDEX
    Explanations

    tracking standards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ورش
    0.46
    䔬
    0.44
     שנ
    0.44
    莪
    0.44
    ن
    0.43
    ೯
    0.43
    ਰੇ
    0.42
    تم
    0.42
    לא
    0.42
     በጥ
    0.42
    POSITIVE LOGITS
     Medicare
    0.47
     physician
    0.47
     presumably
    0.45
     Russia
    0.43
    ですね
    0.42
     Gmail
    0.42
     abroad
    0.42
     Myanmar
    0.42
     Rollins
    0.42
     medicare
    0.41
    Act Density 0.004%

    No Known Activations