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

    Neuronpedia

    INDEX
    Explanations

    units of length

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    мак
    0.40
    prache
    0.39
     artistes
    0.38
    KSprite
    0.38
    දිය
    0.38
    生产
    0.37
    ्तार
    0.37
     Castile
    0.37
     kurang
    0.37
     cones
    0.37
    POSITIVE LOGITS
     CRT
    0.39
     によ
    0.39
    Lines
    0.38
    謝
    0.38
    Proble
    0.38
     ANN
    0.38
     صفحات
    0.38
    Pages
    0.37
    known
    0.37
     విశ
    0.37
    Act Density 0.002%

    No Known Activations