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

    Neuronpedia

    INDEX
    Explanations

    code identifiers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Мон
    -0.07
    ındaki
    -0.06
     fragile
    -0.06
    ském
    -0.06
     completionHandler
    -0.06
     karma
    -0.06
     coveted
    -0.06
    系統
    -0.06
    glm
    -0.06
     diseño
    -0.06
    POSITIVE LOGITS
     prospects
    0.07
    letter
    0.07
     reopen
    0.07
     predicates
    0.06
    ))){↵
    0.06
    zure
    0.06
    BOOT
    0.06
    eft
    0.06
    uspended
    0.06
     butcher
    0.06
    Act Density 0.018%

    No Known Activations