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

    Neuronpedia

    INDEX
    Explanations

    will remember dreams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    は
    0.67
    는
    0.48
    も
    0.48
    是
    0.46
    یه
    0.41
    Karena
    0.40
    ల్లు
    0.39
    은
    0.38
     DHCP
    0.38
    iknya
    0.38
    POSITIVE LOGITS
     三角
    0.52
     特定
    0.48
     впечат
    0.45
     canaliculato
    0.43
     وف
    0.43
     conhecimentos
    0.43
     சுற்றுலா
    0.43
     وث
    0.42
    sbParams
    0.42
     باتوں
    0.42
    Act Density 0.000%

    No Known Activations