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

    Neuronpedia

    INDEX
    Explanations

    golang code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    면서
    0.73
    $('#
    0.71
    『
    0.69
     nascetur
    0.68
    $('
    0.66
    owników
    0.65
    며
    0.64
    အရ
    0.63
    ('/\
    0.62
    oree
    0.62
    POSITIVE LOGITS
     witnessing
    0.68
    PU
    0.67
    ._
    0.67
    _)
    0.66
    unci
    0.64
    िरण
    0.64
    )_
    0.63
    _"
    0.62
     scared
    0.62
    rać
    0.62
    Act Density 0.002%

    No Known Activations