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

    Neuronpedia

    INDEX
    Explanations

    technical writing

    np_max-act · gemini-2.0-flash

    This neuron activates on words indicating repetition (e.g. “repeating”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     looping
    -0.06
     Paşa
    -0.06
    ल
    -0.06
    maktan
    -0.06
     equitable
    -0.06
    ВС
    -0.06
    ,text
    -0.05
    /NĐ
    -0.05
     Kas
    -0.05
    cts
    -0.05
    POSITIVE LOGITS
     condo
    0.07
     experimented
    0.07
     yielding
    0.07
    di
    0.07
     binds
    0.06
     fundra
    0.06
    ictured
    0.06
    (_.
    0.06
    Agent
    0.06
    _seed
    0.06
    Act Density 0.006%

    No Known Activations