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

    Neuronpedia

    INDEX
    Explanations

    Ar and related words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aVal
    0.40
    西兰
    0.39
    敺
    0.39
    琹
    0.38
     杨
    0.38
    迪士
    0.38
    潍
    0.38
    塀
    0.37
    輋
    0.37
    ⠿
    0.37
    POSITIVE LOGITS
     Ар
    2.47
     ар
    2.28
    Ар
    2.22
    Ar
    2.05
     AR
    2.05
    アー
    1.95
     Arsen
    1.91
     Arlington
    1.90
     אר
    1.88
     Arsenal
    1.77
    Act Density 0.116%

    No Known Activations