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

    Neuronpedia

    INDEX
    Explanations

    Iroquois, blue jays, magnetosphere

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    0.82
     I
    0.80
    <0x0D>
    0.79
    ě
    0.74
    2
    0.73
    ail
    0.70
    4
    0.69
    </h2>
    0.68
    age
    0.68
    ien
    0.68
    POSITIVE LOGITS
    在
    0.92
    も
    0.86
    ла
    0.80
     in
    0.79
    ও
    0.77
    ある
    0.75
    도
    0.73
    getCql
    0.71
     রহিল
    0.66
    在国内
    0.66
    Act Density 0.001%

    No Known Activations