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

    Neuronpedia

    INDEX
    Explanations

    dates, values, and management

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    itriangular
    1.39
    𝑆
    1.39
     `<`,
    1.39
     төр
    1.35
     непре
    1.35
    elapse
    1.34
    𝗡
    1.32
    𝐺
    1.32
    𝐷
    1.29
    Conservation
    1.28
    POSITIVE LOGITS
    高
    0.87
    这是一个
    0.86
    那就是
    0.84
     niche
    0.82
    ️
    0.81
    iz
    0.81
     disco
    0.80
    arena
    0.80
     st
    0.80
     Jan
    0.80
    Act Density 0.000%

    No Known Activations