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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     verified
    -0.07
     خاص
    -0.06
    BW
    -0.06
     troubled
    -0.06
     чувств
    -0.06
    字符
    -0.06
     leader
    -0.06
     prominent
    -0.06
    ối
    -0.06
     generated
    -0.06
    POSITIVE LOGITS
     excer
    0.07
    ná
    0.07
     돌
    0.06
    صات
    0.06
    _cores
    0.06
    --)
↵
    0.06
    )})↵
    0.06
    collection
    0.06
    ("/");↵
    0.06
    breaking
    0.06
    Act Density 0.140%

    No Known Activations