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

    Neuronpedia

    INDEX
    Explanations

    obey

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lerimiz
    -0.07
    amac
    -0.06
    aklı
    -0.06
    eným
    -0.06
     happiness
    -0.06
    ание
    -0.06
    DataContract
    -0.06
     obsc
    -0.06
     ιστο
    -0.06
    遇
    -0.06
    POSITIVE LOGITS
     Rus
    0.07
     russe
    0.07
    lage
    0.07
     елем
    0.07
        ↵↵↵
    0.06
     něj
    0.06
    _level
    0.06
    ...")↵
    0.06
    .Integer
    0.06
    NotFoundException
    0.06
    Act Density 0.234%

    No Known Activations