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

    Neuronpedia

    INDEX
    Explanations

    brackets

    np_max-act · gemini-2.0-flash

    The neuron is looking for LaTeX macro‐definition commands (e.g. “\newcommand{…}{…}”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    436
    -0.06
    ocr
    -0.06
     Shoes
    -0.06
    ducted
    -0.06
    (h
    -0.06
     متخصص
    -0.06
     kiếm
    -0.06
     ms
    -0.06
     فه
    -0.05
    boBox
    -0.05
    POSITIVE LOGITS
     Unsafe
    0.07
     packet
    0.07
     slamming
    0.07
    lení
    0.07
     апр
    0.06
    .VALUE
    0.06
    (Py
    0.06
     booths
    0.06
    .setId
    0.06
     arguments
    0.06
    Act Density 0.002%

    No Known Activations