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

    Neuronpedia

    INDEX
    Explanations

    Technical articles

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of large language models (LLMs)—their acronyms and specific model names (e.g. Dolly-V2, LLaMA, Koala, GPT4All, Vicuna).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    所以
    -0.07
    Update
    -0.06
    142
    -0.06
    _updated
    -0.06
    との
    -0.06
     Majesty
    -0.06
     Mahar
    -0.06
     successors
    -0.06
    stateProvider
    -0.06
    \Domain
    -0.06
    POSITIVE LOGITS
     setVisible
    0.07
    oreal
    0.07
    ait
    0.06
     […
    0.06
     (--
    0.06
     özellikleri
    0.06
     Recon
    0.06
     GS
    0.06
     prostřed
    0.06
    ']
↵
↵
    0.06
    Act Density 0.097%

    No Known Activations