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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _bn
    -0.06
     Российской
    -0.06
    öy
    -0.06
    oren
    -0.06
     convey
    -0.06
     Modern
    -0.06
     potato
    -0.06
     Cambodia
    -0.06
     Chap
    -0.06
     Trans
    -0.06
    POSITIVE LOGITS
     Invoice
    0.06
    <dim
    0.06
    抬
    0.06
     Emirates
    0.06
     کار
    0.06
     annotations
    0.06
     atheists
    0.06
     कथ
    0.06
     всі
    0.06
     smirk
    0.06
    Act Density 0.000%

    No Known Activations