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

    Neuronpedia

    INDEX
    Explanations

    Articles

    np_max-act · gemini-2.0-flash

    The neuron flags mentions of specific publication or source names (e.g. journal, newspaper, or other cited outlet titles).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    けれど
    -0.07
    Atoms
    -0.07
    -0.06
    -choice
    -0.06
    	tree
    -0.06
    .JSON
    -0.06
    ')">
    -0.06
    woord
    -0.06
    一个人
    -0.06
     plist
    -0.06
    POSITIVE LOGITS
    日本
    0.07
    бас
    0.06
    .py
    0.06
     mHandler
    0.06
    :bg
    0.06
    occ
    0.06
     legit
    0.06
    owy
    0.06
     материала
    0.06
    搜
    0.06
    Act Density 0.033%

    No Known Activations