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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens containing a decimal point (i.e. floating‐point version numbers in license headers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .:.:.:
    -0.08
    Beans
    -0.07
    .HasValue
    -0.07
    �
    -0.06
     quarterback
    -0.06
    akan
    -0.06
     dil
    -0.06
    )=
    -0.06
     Sept
    -0.06
    ＝
    -0.06
    POSITIVE LOGITS
     TRY
    0.07
    completion
    0.07
     adjustable
    0.06
    บาย
    0.06
     drafting
    0.06
    	info
    0.06
     نویس
    0.06
     Plug
    0.06
     completion
    0.06
    蒂
    0.06
    Act Density 0.002%

    No Known Activations