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

    Neuronpedia

    INDEX
    Explanations

    Himal

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect geographical place names—especially references to the Himalayas and related South Asian locations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _tag
    -0.07
     Girls
    -0.07
    wner
    -0.06
    ؤال
    -0.06
    HORT
    -0.06
    .getTitle
    -0.06
    Flight
    -0.06
    侵
    -0.06
    -dark
    -0.06
    -store
    -0.06
    POSITIVE LOGITS
     Mediterranean
    0.07
    道
    0.07
    SAME
    0.07
    ůže
    0.06
     Himal
    0.06
    toArray
    0.06
     cosmos
    0.06
    ें।↵
    0.06
    IDS
    0.06
    possible
    0.06
    Act Density 0.021%

    No Known Activations