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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (part
    -0.07
     jitter
    -0.07
     musí
    -0.06
     Chính
    -0.06
    από
    -0.06
    (Program
    -0.06
    URLRequest
    -0.06
     denně
    -0.06
    (isolate
    -0.06
    grades
    -0.06
    POSITIVE LOGITS
    ottenham
    0.07
    EA
    0.07
     Sheikh
    0.07
    ény
    0.06
     emotionally
    0.06
     eighty
    0.06
     Emirates
    0.06
    qt
    0.06
    61
    0.06
     UserService
    0.06
    Act Density 0.002%

    No Known Activations