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

    Neuronpedia

    INDEX
    Explanations

    yaml code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     разрабаты
    0.85
     разработан
    0.84
     Каждый
    0.84
     fortunate
    0.83
    перы
    0.77
     seminars
    0.75
     acontece
    0.75
     организова
    0.75
     журнала
    0.73
     выстав
    0.73
    POSITIVE LOGITS
    CAR
    1.01
    enthic
    0.88
    conten
    0.86
    id
    0.85
    しばらく
    0.84
    ގ
    0.81
    getRandom
    0.81
    akang
    0.80
    intl
    0.79
    intens
    0.78
    Act Density 0.001%

    No Known Activations