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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dư�
    -0.07
     whence
    -0.06
    少し
    -0.06
     Fant
    -0.06
     hardwood
    -0.06
     deposits
    -0.06
     가지고
    -0.06
     Immediate
    -0.06
    itle
    -0.06
    ющ
    -0.06
    POSITIVE LOGITS
     �
    0.07
     testimonials
    0.07
     história
    0.07
    ीआई
    0.07
     ख
    0.07
    mpz
    0.06
    asia
    0.06
     filing
    0.06
    Jason
    0.06
    _letter
    0.06
    Act Density 0.003%

    No Known Activations