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

    Neuronpedia

    INDEX
    Explanations

    look

    np_max-act · gemini-2.0-flash

    The neuron fires most strongly on descriptive modifiers—especially adjectives and adverbs that convey qualities or characteristics.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ipmap
    -0.07
    .Help
    -0.07
    Three
    -0.06
    ôi
    -0.06
     toolbar
    -0.06
    243
    -0.06
    theme
    -0.06
    كون
    -0.06
    ्पन
    -0.06
    uff
    -0.06
    POSITIVE LOGITS
    <std
    0.07
    -ranging
    0.07
    _linked
    0.06
     등장
    0.06
     statewide
    0.06
    쟁
    0.06
    (nd
    0.06
     intrig
    0.06
     restriction
    0.06
     performing
    0.06
    Act Density 0.174%

    No Known Activations