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

    Neuronpedia

    INDEX
    Explanations

    avoiding harmful content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    1.46
    p
    1.18
    y
    1.16
    el
    1.13
    f
    1.09
    h
    1.05
    x
    1.04
    ec
    1.03
     dealings
    1.02
    in
    1.00
    POSITIVE LOGITS
    𝗮
    1.34
    𝓸
    1.30
     नजदी
    1.29
    𝐚
    1.24
     а
    1.21
     sœurs
    1.20
     améric
    1.19
    𝓲
    1.16
    𝓪
    1.13
    എന്ന
    1.13
    Act Density 0.827%

    No Known Activations