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

    Neuronpedia

    INDEX
    Explanations

    see ya

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Hawke
    0.39
    bildung
    0.37
     Jem
    0.37
    वड
    0.36
    <unused25>
    0.35
     Firth
    0.35
    Abasis
    0.35
     Pilates
    0.35
    тости
    0.34
    㽞
    0.34
    POSITIVE LOGITS
     ya
    3.00
     Ya
    2.86
    Ya
    2.83
    ya
    2.59
     YA
    2.47
    YA
    2.41
     يا
    2.30
     я
    2.14
     yah
    2.05
    ヤ
    2.05
    Act Density 0.022%

    No Known Activations