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

    Neuronpedia

    INDEX
    Explanations

    double negative, redundant phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rendelkez
    0.49
     renewables
    0.48
     conversions
    0.45
    <start_of_image>
    0.45
     flexibility
    0.44
     transitioned
    0.44
     voldo
    0.44
     synergies
    0.43
     unil
    0.43
     inkl
    0.43
    POSITIVE LOGITS
     poisonous
    0.47
     worsen
    0.47
    nte
    0.46
     ಸಮಸ್ಯ
    0.45
    ׁ
    0.45
     poisoning
    0.45
     ઘરે
    0.44
     murderous
    0.44
     божомол
    0.43
    cı
    0.43
    Act Density 0.015%

    No Known Activations