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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    untary
    -0.08
    icer
    -0.07
     warming
    -0.07
    온
    -0.07
    .spec
    -0.07
     Manifest
    -0.07
     empirical
    -0.07
     PCs
    -0.07
    ระ
    -0.06
    .party
    -0.06
    POSITIVE LOGITS
    페이지
    0.07
    Denver
    0.07
     дій
    0.07
     ηλεκ
    0.07
    especially
    0.07
     будто
    0.06
     Ident
    0.06
     тисяч
    0.06
    .rot
    0.06
    %;"
    0.06
    Act Density 0.075%

    No Known Activations