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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    statements conveying a middling, neutral appraisal in reviews—indicating something is acceptable or average rather than excellent or poor.

    oai_token-act-pair · gpt-5Triggered by @yooniel31
    New Auto-Interp
    Negative Logits
     immersion
    -0.07
    Base
    -0.07
    bash
    -0.07
    寻
    -0.06
     Burr
    -0.06
     프로
    -0.06
     تور
    -0.06
    ma
    -0.06
     proportions
    -0.06
     unordered
    -0.06
    POSITIVE LOGITS
     cevap
    0.07
     للح
    0.07
    _YEAR
    0.06
    BootTest
    0.06
    ΙΟΥ
    0.06
    止
    0.06
    .partial
    0.06
    .des
    0.06
    (spec
    0.06
    nowledge
    0.06
    Act Density 0.090%

    No Known Activations