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

    Neuronpedia

    INDEX
    Explanations

    code/software

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    одо
    -0.07
    �
    -0.06
    ораль
    -0.06
    طان
    -0.06
    _REGS
    -0.06
     lamb
    -0.06
     ordeal
    -0.06
     ملي
    -0.06
     Indonesian
    -0.06
     Kuala
    -0.06
    POSITIVE LOGITS
     professors
    0.06
     Arthropoda
    0.06
     rider
    0.06
     joyful
    0.06
     lẽ
    0.06
     (.
    0.06
    없이
    0.06
     requesting
    0.06
    workflow
    0.06
    IFIED
    0.06
    Act Density 0.000%

    No Known Activations