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

    Neuronpedia

    INDEX
    Explanations

    mü/mu with umlauts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Enum
    0.38
    ENAME
    0.37
    넘
    0.36
    ומ
    0.36
     zat
    0.35
    lice
    0.35
    splitting
    0.35
    ฎ
    0.34
    aru
    0.34
     وسلم
    0.34
    POSITIVE LOGITS
    gean
    0.57
    cade
    0.46
    esses
    0.44
     дав
    0.40
    rette
    0.39
    باح
    0.38
     hick
    0.38
     intrusions
    0.38
     litig
    0.37
     hits
    0.37
    Act Density 0.001%

    No Known Activations