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

    Neuronpedia

    INDEX
    Explanations

    Fantasy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alles
    -0.06
     helicopters
    -0.06
    μ
    -0.06
    salary
    -0.06
    medical
    -0.06
    ją
    -0.06
    .Internal
    -0.06
     lesbians
    -0.06
    oxid
    -0.06
     uranium
    -0.06
    POSITIVE LOGITS
    urdy
    0.07
    cased
    0.06
    рг
    0.06
    ++.
    0.06
    >'.
    0.06
    atty
    0.06
    uto
    0.06
    stem
    0.06
    											↵
    0.06
     Numerous
    0.06
    Act Density 0.000%

    No Known Activations