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

    Neuronpedia

    INDEX
    Explanations

    dimensions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Fire
    -0.08
     pu
    -0.07
    𝐡
    -0.07
    �
    -0.07
    .Millisecond
    -0.06
    .slides
    -0.06
     Buffered
    -0.06
    @Api
    -0.06
     epochs
    -0.06
     Conj
    -0.06
    POSITIVE LOGITS
    ています
    0.08
    rawn
    0.07
    되었다
    0.07
     metabolism
    0.07
    한다
    0.07
    wood
    0.07
    销量
    0.07
    onz
    0.06
    /buttons
    0.06
    0.06
    Act Density 0.008%

    No Known Activations