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

    Neuronpedia

    INDEX
    Explanations

    delimiters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    shirt
    -0.07
    ίος
    -0.07
    民主
    -0.06
     Religious
    -0.06
     translator
    -0.06
     BMC
    -0.06
    ادات
    -0.06
    iates
    -0.06
    ipherals
    -0.06
    shoot
    -0.06
    POSITIVE LOGITS
    cce
    0.07
     cambi
    0.06
    ese
    0.06
     Functions
    0.06
    _queue
    0.06
     виде
    0.06
    .jpeg
    0.06
     handwriting
    0.06
     اختلاف
    0.06
     redesigned
    0.06
    Act Density 0.017%

    No Known Activations