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

    Neuronpedia

    INDEX
    Explanations

    icks

    np_max-act · gemini-2.0-flash

    The neuron detects title-cased names of creative works (e.g., books, albums, series, programs).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     të
    -0.07
     acid
    -0.07
    /min
    -0.07
    _vi
    -0.07
     complet
    -0.06
     Ευ
    -0.06
    	ct
    -0.06
    ชนะ
    -0.06
    /non
    -0.06
    	cnt
    -0.06
    POSITIVE LOGITS
    */
↵
    0.07
    ');</
    0.07
     localObject
    0.06
    しました
    0.06
     :)
    0.06
    codigo
    0.06
     �
    0.06
    question
    0.06
     вона
    0.06
     就
    0.06
    Act Density 0.019%

    No Known Activations