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

    Neuronpedia

    INDEX
    Explanations

    research

    np_max-act · gemini-2.0-flash

    The neuron flags phrases where the writer refers to their own investigative process (e.g. “I did some research,” “after some trial and error,” “I discovered”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    avid
    -0.07
     ConsoleColor
    -0.06
     で
    -0.06
     Ảnh
    -0.06
    دة
    -0.06
    ored
    -0.06
     Encryption
    -0.06
     cắt
    -0.06
    ipients
    -0.06
     supportive
    -0.06
    POSITIVE LOGITS
    ráf
    0.08
    .พ
    0.07
    永
    0.07
     Summit
    0.07
    碎
    0.07
    _bm
    0.07
     heterogeneous
    0.06
     pound
    0.06
     mainland
    0.06
    více
    0.06
    Act Density 0.022%

    No Known Activations