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

    Neuronpedia

    INDEX
    Explanations

    phrases related to identity and existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    is a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.59
    aarrggbb
    -0.56
     ProtoMessage
    -0.56
    PyExc
    -0.56
    DoubleQuotes
    -0.55
    RenderAtEndOf
    -0.54
    ніципалі
    -0.52
    gameserver
    -0.50
    RegistryLite
    -0.49
    RegressionTest
    -0.49
    POSITIVE LOGITS
    是个
    0.45
    是個
    0.43
     เป็น
    0.38
     berupa
    0.37
    เป็น
    0.37
    entibus
    0.37
     orejas
    0.34
    จะเป็น
    0.34
     Certified
    0.33
    deepEqual
    0.33
    Act Density 0.377%

    No Known Activations