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

    Neuronpedia

    INDEX
    Explanations

    the repetition of specific phonetic or character patterns in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    アズサはず

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CloseOperation
    -0.42
     אות
    -0.41
     herr
    -0.37
     principal
    -0.36
     effectively
    -0.34
     princip
    -0.33
     principle
    -0.33
     ACCOM
    -0.32
    {"
    -0.32
    comp
    -0.32
    POSITIVE LOGITS
     ز
    1.75
    ز
    1.46
     الز
    1.24
     ז
    0.89
    ז
    0.80
     Z
    0.77
    getZ
    0.75
     بز
    0.73
    ズ
    0.71
     ズ
    0.69
    Act Density 0.002%

    No Known Activations