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

    Neuronpedia

    INDEX
    Explanations

    Planned

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鐟
    0.63
     folgen
    0.61
    𝐯
    0.61
     blankets
    0.59
     tehd
    0.58
    𒉿
    0.58
     dilwale
    0.57
     ट्रक
    0.57
    릭
    0.57
    কর
    0.56
    POSITIVE LOGITS
    home
    0.67
    publish
    0.63
    upload
    0.62
    either
    0.62
     either
    0.61
     дома
    0.61
     заинтересо
    0.59
     случайно
    0.59
    phys
    0.58
     வெளியிட
    0.58
    Act Density 0.002%

    No Known Activations