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

    Neuronpedia

    INDEX
    Explanations

    HTML tags

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spooky
    -0.07
     dancer
    -0.07
    '):
    -0.06
     eup
    -0.06
    /articles
    -0.06
    люч
    -0.06
    ')."
    -0.06
    โอ
    -0.06
    :")
    -0.06
    _remote
    -0.06
    POSITIVE LOGITS
    vx
    0.06
    we
    0.06
     dysfunction
    0.06
    чна
    0.06
    .Bind
    0.06
    вая
    0.06
    кра
    0.06
    атов
    0.06
    ef
    0.06
    .getSelected
    0.06
    Act Density 0.002%

    No Known Activations