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

    Neuronpedia

    INDEX
    Explanations

    K

    np_max-act · gemini-2.0-flash

    This neuron fires on isolated single‐character tokens—most often uppercase Latin letters or single Katakana characters.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    زان
    -0.07
     Terminator
    -0.07
    榜
    -0.07
    ramid
    -0.06
    사는
    -0.06
     Pyramid
    -0.06
     Tourism
    -0.06
    antine
    -0.06
    Gün
    -0.06
     magazines
    -0.06
    POSITIVE LOGITS
    .raises
    0.07
    	DBG
    0.07
    grad
    0.06
     Gui
    0.06
     �
    0.06
    /')↵
    0.06
    Dao
    0.06
    <bool
    0.06
    (results
    0.06
     外部リンク
    0.06
    Act Density 0.249%

    No Known Activations