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

    Neuronpedia

    INDEX
    Explanations

    micro, michel, michael, microsoft

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    琕
    0.51
    لیل
    0.41
     социально
    0.41
    %@",
    0.39
     absolument
    0.39
     बिल्कुल
    0.39
    ביל
    0.38
    mere
    0.38
    イギリス
    0.38
    ヴィ
    0.37
    POSITIVE LOGITS
    angelo
    0.66
     Mike
    0.65
     microp
    0.58
     mik
    0.58
    Mike
    0.57
     mike
    0.55
     mic
    0.55
     micro
    0.52
     Mic
    0.48
     MIC
    0.48
    Act Density 0.014%

    No Known Activations