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

    Neuronpedia

    INDEX
    Explanations

    signs of harm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    embe
    0.44
     shame
    0.41
    ên
    0.40
     platforms
    0.40
    パートナー
    0.39
    越
    0.39
     metadata
    0.39
     strukt
    0.38
    shade
    0.38
     соответствует
    0.37
    POSITIVE LOGITS
    μι
    0.60
     ৷
    0.47
    rokken
    0.47
    ቝ
    0.46
    ’
    0.45
    ۤ
    0.45
     Україні
    0.45
     nvp
    0.44
    HasStarred
    0.44
     Corbyn
    0.44
    Act Density 0.000%

    No Known Activations