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

    Neuronpedia

    INDEX
    Explanations

    Chinese characters and words related to types and fields

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

    character or word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __':
    -0.56
    __":
    -0.56
    __":
    -0.51
     Ens
    -0.50
     चीज़ों
    -0.48
    揄
    -0.47
    gliere
    -0.46
    >
    -0.46
     unsuccessfully
    -0.46
     Velasco
    -0.45
    POSITIVE LOGITS
    字
    2.25
     字
    1.53
    文字
    1.09
     word
    0.96
     文字
    0.86
    字体
    0.86
     WORD
    0.84
     words
    0.81
    Word
    0.80
     chữ
    0.79
    Act Density 0.006%

    No Known Activations