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

    Neuronpedia

    INDEX
    Explanations

    words starting with U

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    สาร
    0.44
    Tür
    0.40
    尕
    0.39
    Pink
    0.36
    ről
    0.36
    棭
    0.36
    。",
    0.36
    ک
    0.36
     Saxony
    0.35
    تن
    0.35
    POSITIVE LOGITS
     U
    0.91
     Ud
    0.55
     Ub
    0.55
     UR
    0.55
     ইউ
    0.53
    trasound
    0.53
     UD
    0.53
     UF
    0.52
     Uda
    0.51
    ploader
    0.50
    Act Density 0.044%

    No Known Activations