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

    Neuronpedia

    INDEX
    Explanations

    less than or rather than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     débar
    0.40
    ograph
    0.39
    ToWrite
    0.39
     geldi
    0.37
     များ
    0.37
     maaaring
    0.37
     Decorations
    0.36
     Schl
    0.36
     CW
    0.36
     phụ
    0.36
    POSITIVE LOGITS
     সবে
    0.39
    에서도
    0.39
     gdje
    0.38
    亀
    0.37
    NONE
    0.37
    全球
    0.37
     galore
    0.37
    ">-
    0.35
    בק
    0.35
     где
    0.35
    Act Density 0.002%

    No Known Activations