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

    Neuronpedia

    INDEX
    Explanations

    Book titles

    np_max-act · gemini-2.0-flash

    This neuron identifies occurrences of book or series titles (multiword capitalized proper names) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _words
    -0.08
    -like
    -0.06
    leDb
    -0.06
    posal
    -0.06
    usiness
    -0.06
    ekyll
    -0.06
    OutOfRangeException
    -0.06
     Hide
    -0.06
    เท
    -0.06
    linewidth
    -0.06
    POSITIVE LOGITS
    	Action
    0.07
     favored
    0.07
    ulin
    0.06
     presumed
    0.06
     derece
    0.06
     arts
    0.06
     das
    0.06
    	or
    0.06
     mention
    0.06
    razione
    0.06
    Act Density 0.008%

    No Known Activations