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

    Neuronpedia

    INDEX
    Explanations

    save the code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     잠
    0.75
     awaiting
    0.68
     mort
    0.66
     swiftly
    0.65
     dangerously
    0.64
     parallax
    0.63
     Resident
    0.63
    闩
    0.62
     further
    0.62
     thereafter
    0.61
    POSITIVE LOGITS
    above
    0.83
    上記
    0.83
     acima
    0.81
    上面的
    0.79
    ghe
    0.73
    odio
    0.72
    上面
    0.72
    以上
    0.71
     любую
    0.71
     above
    0.71
    Act Density 0.012%

    No Known Activations