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

    Neuronpedia

    INDEX
    Explanations

    countries

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    束
    -0.07
    Unchecked
    -0.07
    formulario
    -0.06
    	ev
    -0.06
     клу
    -0.06
    بش
    -0.06
    Birthday
    -0.06
    Gas
    -0.06
    _stdout
    -0.06
     ون
    -0.06
    POSITIVE LOGITS
     exposing
    0.07
     трансп
    0.06
    ption
    0.06
    atching
    0.06
    <Component
    0.06
     ACS
    0.06
    .Empty
    0.06
     преж
    0.06
     "()
    0.06
     Değer
    0.06
    Act Density 0.018%

    No Known Activations