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

    Neuronpedia

    INDEX
    Explanations

    swearing and vulgarity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    src
    0.38
     சார
    0.36
    ຕ້ອງການ
    0.36
     strange
    0.36
    INTE
    0.36
     pedibusque
    0.35
    rather
    0.34
    ONE
    0.34
     आवश्यक
    0.33
    髖
    0.33
    POSITIVE LOGITS
     garbage
    0.64
    heap
    0.63
     piled
    0.57
     heap
    0.55
    garbage
    0.55
    pile
    0.54
    storms
    0.54
     smeared
    0.54
    🗑
    0.54
     fest
    0.53
    Act Density 0.022%

    No Known Activations