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

    Neuronpedia

    INDEX
    Explanations

    years ending in 8

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ্ড
    1.73
    )。
    1.73
    此之外
    1.63
     saucepan
    1.58
     palt
    1.55
    爀
    1.52
    );\
    1.52
    。(
    1.50
    на
    1.49
     acuity
    1.45
    POSITIVE LOGITS
    t
    2.73
    id
    2.14
    tól
    1.89
    y
    1.84
    dan
    1.84
    tir
    1.78
    e
    1.78
    don
    1.77
    ri
    1.74
    tone
    1.73
    Act Density 0.100%

    No Known Activations