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

    Neuronpedia

    INDEX
    Explanations

    self

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Slut
    -0.07
    ического
    -0.06
     Cold
    -0.06
     TokenType
    -0.06
     stret
    -0.06
    $route
    -0.06
     Plastic
    -0.06
     těl
    -0.06
    Convert
    -0.06
    emente
    -0.05
    POSITIVE LOGITS
    (slice
    0.07
    ：<
    0.07
     Adoption
    0.07
     hyperlink
    0.07
     ([
    0.06
     mixins
    0.06
     พฤศจ
    0.06
     dif
    0.06
    errated
    0.06
    §
    0.06
    Act Density 0.176%

    No Known Activations