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

    Neuronpedia

    INDEX
    Explanations

    fast movement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uação
    0.59
    рен
    0.58
    НА
    0.58
    Excerpt
    0.57
    ┴
    0.57
    ем
    0.57
     Kabhi
    0.57
    igslist
    0.57
    pannt
    0.56
    сс
    0.56
    POSITIVE LOGITS
     women
    0.77
     sport
    0.74
     subject
    0.72
     adults
    0.70
     flock
    0.69
     flocks
    0.68
     colonists
    0.68
     Women
    0.67
     fle
    0.67
     나머지
    0.66
    Act Density 0.001%

    No Known Activations