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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    punctuation and connective markers that indicate sentence or clause boundaries.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    forme
    -0.07
     Coffee
    -0.06
    立て
    -0.06
    管理
    -0.06
    デ
    -0.06
     hello
    -0.06
     نزد
    -0.06
     मध
    -0.06
    _BLEND
    -0.06
     rain
    -0.06
    POSITIVE LOGITS
    _tuple
    0.06
    egot
    0.06
    =user
    0.06
     ISP
    0.06
    Svg
    0.06
     sider
    0.06
     nalez
    0.06
    -channel
    0.06
     opponent
    0.06
    Copyright
    0.06
    Act Density 0.629%

    No Known Activations