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

    Neuronpedia

    INDEX
    Explanations

    fundamentals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ีซ
    -0.06
     injustice
    -0.06
    を作
    -0.06
    =rand
    -0.06
    گل
    -0.06
    ../../../
    -0.06
    spam
    -0.06
     ๆ
    -0.06
    _gt
    -0.06
     ذکر
    -0.06
    POSITIVE LOGITS
     Margin
    0.06
    Hugh
    0.06
    、小
    0.06
     signage
    0.06
    _SERVICE
    0.06
     Nous
    0.06
    ảng
    0.06
    ющими
    0.06
    IDL
    0.06
    Billing
    0.06
    Act Density 0.174%

    No Known Activations