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

    Neuronpedia

    INDEX
    Explanations

    ements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $class
    -0.07
    munition
    -0.07
     embrace
    -0.07
     за
    -0.07
    .closed
    -0.07
    ули
    -0.06
     قدر
    -0.06
     Chess
    -0.06
     sur
    -0.06
     unleash
    -0.06
    POSITIVE LOGITS
    	cout
    0.07
     birthdays
    0.07
     Hear
    0.06
     ощущ
    0.06
    seed
    0.06
    272
    0.06
    ерп
    0.06
     Ha
    0.06
    вать
    0.06
     Link
    0.06
    Act Density 0.000%

    No Known Activations