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

    Neuronpedia

    INDEX
    Explanations

    Latin snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     objectId
    -0.08
    ocket
    -0.08
    沮丧
    -0.07
    LogFile
    -0.07
    炱
    -0.07
    .getD
    -0.07
    汞
    -0.07
    愕
    -0.06
    .CopyTo
    -0.06
    .Immutable
    -0.06
    POSITIVE LOGITS
     Rudd
    0.07
     TRI
    0.07
     Cruise
    0.06
    〰
    0.06
    multi
    0.06
    重启
    0.06
     dị
    0.06
    '")↵
    0.06
     компании
    0.06
     Concat
    0.06
    Act Density 0.001%

    No Known Activations