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

    Neuronpedia

    INDEX
    Explanations

    enumerating lists

    np_max-act · gemini-2.0-flash

    The neuron activates on the word “including” (and similar list‐intro phrases) used to introduce examples or list items.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     lParam
    -0.06
     Angiosper
    -0.06
     батьків
    -0.06
     IIC
    -0.06
    oses
    -0.06
     Cardinal
    -0.06
     чого
    -0.06
     Regex
    -0.06
    GRAPH
    -0.06
    _TH
    -0.06
    POSITIVE LOGITS
    	manager
    0.06
    _accounts
    0.06
    .lifecycle
    0.06
     deterioration
    0.06
     feast
    0.06
     createContext
    0.06
    _pressure
    0.06
    (freq
    0.06
     backing
    0.06
     част
    0.06
    Act Density 0.073%

    No Known Activations