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

    Neuronpedia

    INDEX
    Explanations

    scientific papers citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kaz
    -0.07
    aware
    -0.07
    'av
    -0.07
    kemiz
    -0.06
     Sphinx
    -0.06
    mony
    -0.06
    Bug
    -0.06
    astered
    -0.06
    yar
    -0.06
    RIORITY
    -0.06
    POSITIVE LOGITS
    peek
    0.07
    έλ
    0.06
    Endian
    0.06
     tông
    0.06
    �
    0.06
    London
    0.06
    �
    0.06
    .webdriver
    0.06
     router
    0.06
    _save
    0.06
    Act Density 0.000%

    No Known Activations