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

    Neuronpedia

    INDEX
    Explanations

    code/technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    こ
    -0.06
    udo
    -0.06
     oat
    -0.06
    ्व
    -0.06
    ょう
    -0.06
    (fixture
    -0.06
    _Filter
    -0.06
     OU
    -0.06
    アル
    -0.06
     بيت
    -0.06
    POSITIVE LOGITS
    	Transform
    0.07
    říz
    0.07
     instrumentation
    0.06
     assessing
    0.06
     Give
    0.06
     >=
    0.06
    mx
    0.06
    -inch
    0.06
     remove
    0.06
     витами
    0.06
    Act Density 0.000%

    No Known Activations