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

    Neuronpedia

    INDEX
    Explanations

    .com

    np_max-act · gemini-2.0-flash

    identify parts of web/documentation URLs (tokens that are components of links).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    frame
    -0.07
    infile
    -0.06
    сов
    -0.06
    _library
    -0.06
     gore
    -0.06
     stitched
    -0.06
     VIR
    -0.06
    bugs
    -0.06
     Audience
    -0.06
     swelling
    -0.06
    POSITIVE LOGITS
    /components
    0.06
    기에
    0.06
     mutableListOf
    0.06
    .Experimental
    0.06
    那样
    0.06
    	dp
    0.06
    _UNDER
    0.06
     residences
    0.06
    ensem
    0.06
    .PER
    0.06
    Act Density 0.000%

    No Known Activations