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

    Neuronpedia

    INDEX
    Explanations

    HTML/XML tags

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :str
    -0.06
     ري
    -0.06
     DWC
    -0.06
     Sweet
    -0.06
    notEmpty
    -0.06
     LATIN
    -0.06
    .yang
    -0.06
     отримання
    -0.06
     aerial
    -0.06
     complimentary
    -0.06
    POSITIVE LOGITS
    ematics
    0.08
    atically
    0.07
     повинні
    0.07
    conda
    0.07
    قيقة
    0.07
    illage
    0.07
    ộ
    0.07
    無料
    0.07
     että
    0.07
    laughter
    0.06
    Act Density 0.136%

    No Known Activations