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

    Neuronpedia

    INDEX
    Explanations

    uranium enrichment nuclear proliferation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     grandeur
    1.48
     adrenal
    1.45
    ɴ
    1.38
     sublime
    1.37
     nature
    1.35
     continental
    1.35
     inset
    1.34
    ன்
    1.32
     lesión
    1.32
     parade
    1.32
    POSITIVE LOGITS
    |\
    1.46
    ad
    1.41
    ES
    1.32
    tekn
    1.31
    twenty
    1.30
    𝘆
    1.27
    thirty
    1.25
    yog
    1.22
    𝗶
    1.21
    Tub
    1.21
    Act Density 0.002%

    No Known Activations