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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    This neuron detects the phrase “How to” at the start of a question, marking how-to or “how do I” queries.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Gand
    -0.06
    .fft
    -0.06
     AIS
    -0.06
     이것
    -0.06
    urd
    -0.06
    、その
    -0.06
    vá
    -0.06
    _note
    -0.06
     Mara
    -0.06
    Log
    -0.06
    POSITIVE LOGITS
    comma
    0.06
    (instruction
    0.06
    bitmap
    0.06
    acomment
    0.06
    remark
    0.06
    :black
    0.06
     psz
    0.06
    (any
    0.06
    SSF
    0.06
    createUrl
    0.06
    Act Density 0.023%

    No Known Activations