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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Marriott
    -0.07
    sequences
    -0.07
     finances
    -0.06
     Printf
    -0.06
    yd
    -0.06
    tx
    -0.06
     shoppers
    -0.06
    gression
    -0.06
    maktan
    -0.06
    roids
    -0.06
    POSITIVE LOGITS
     الشر
    0.06
     conse
    0.06
     лак
    0.06
    _attack
    0.06
    Chef
    0.06
     Geoffrey
    0.06
     perí
    0.06
    办公
    0.06
    .nd
    0.06
     ،
    0.06
    Act Density 0.006%

    No Known Activations