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

    Neuronpedia

    INDEX
    Explanations

    foreign words and character names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Campaign
    0.40
    Tool
    0.40
    hopper
    0.39
     Tool
    0.38
     ویکی
    0.37
     бай
    0.37
    Ậ
    0.37
    ovao
    0.36
    ra
    0.36
    wiki
    0.35
    POSITIVE LOGITS
     superpower
    0.43
     superpowers
    0.42
     Unlike
    0.41
     stamping
    0.41
     meltdown
    0.40
     karakteristik
    0.40
     kasarigan
    0.40
     palav
    0.40
    꿍
    0.40
    Unlike
    0.39
    Act Density 0.002%

    No Known Activations