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

    Neuronpedia

    INDEX
    Explanations

    USDA, Clark, Interior, EP, Canyon, USGS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ня
    1.47
     Zucker
    1.46
    ی
    1.45
     kald
    1.42
    𝙞
    1.42
     Qué
    1.41
     crème
    1.40
    𝔀
    1.39
     Дру
    1.39
    𝒓
    1.38
    POSITIVE LOGITS
    ল
    1.55
    ded
    1.51
    د
    1.46
    lass
    1.45
    นั่ง
    1.45
    Conservation
    1.42
    d
    1.41
    lw
    1.39
    ところが
    1.39
    ड
    1.39
    Act Density 0.024%

    No Known Activations