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

    Neuronpedia

    INDEX
    Explanations

    words starting with Y

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    麝
    0.40
    煖
    0.39
     Hebre
    0.39
    raient
    0.38
    शिवम
    0.38
    ल
    0.38
    ๚
    0.37
    そこに
    0.37
    ኰ
    0.36
    znych
    0.36
    POSITIVE LOGITS
     Y
    0.73
    Y
    0.66
    IELD
    0.56
    psilon
    0.54
     الي
    0.54
    OY
    0.51
     YT
    0.49
    AY
    0.49
    YY
    0.47
     Yn
    0.47
    Act Density 0.094%

    No Known Activations