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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    elements related to humorous or playful concepts.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     incredible
    -0.06
    kB
    -0.06
    [this
    -0.06
     浙江
    -0.06
    reachable
    -0.06
    [Test
    -0.06
     Tree
    -0.06
     grocery
    -0.06
    िभ
    -0.06
     Faster
    -0.06
    POSITIVE LOGITS
    mouth
    0.07
     "
↵
    0.07
    _tip
    0.06
     Quint
    0.06
    utt
    0.06
     chrono
    0.06
    _impl
    0.06
     BMP
    0.06
    Mut
    0.06
     sum
    0.06
    Act Density 0.012%

    No Known Activations