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

    Neuronpedia

    INDEX
    Explanations

    percentage change calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     OU
    -0.08
     UH
    -0.08
     Blake
    -0.08
     bottle
    -0.07
     Uganda
    -0.07
     fug
    -0.07
    消费者
    -0.07
    .portal
    -0.07
    евого
    -0.07
     ministry
    -0.07
    POSITIVE LOGITS
     بنسبة
    0.10
     చెందిన
    0.09
     percentual
    0.08
     financiero
    0.08
     చెంద
    0.08
     halfway
    0.08
     adicional
    0.07
     proportional
    0.07
    額
    0.07
    :+
    0.07
    Act Density 0.025%

    No Known Activations