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

    Neuronpedia

    INDEX
    Explanations

    numbers or quantities represented in a document

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

    Numbers followed by brackets or parentheses

    np_acts-logits-general · gemini-2.0-flash

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     whoſe
    -0.58
    Diweddarwch
    -0.58
     faſt
    -0.54
     himſelf
    -0.54
     Вікіпе
    -0.54
     jeunesse
    -0.54
    apunov
    -0.53
     Fácil
    -0.53
     unſ
    -0.52
     dần
    -0.52
    POSITIVE LOGITS
     للمعارف
    0.70
    ResumeLayout
    0.59
     الحره
    0.59
    httphttps
    0.58
     appelez
    0.57
    findpost
    0.56
    ïlande
    0.55
    mybatisplus
    0.55
    脚注の使い方
    0.55
    SequentialGroup
    0.54
    Act Density 0.535%

    No Known Activations