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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    programming source-code snippets, particularly C/C++/Java-style code blocks with includes, function definitions, and brace-heavy syntax.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    	iNdEx
    -0.07
    imetype
    -0.07
    傲
    -0.07
    (requestCode
    -0.07
    /".$
    -0.07
    僇
    -0.07
    (isolate
    -0.07
     do
    -0.07
    (de
    -0.07
    总理
    -0.07
    POSITIVE LOGITS
     Munich
    0.07
    bullet
    0.07
     dar
    0.07
    排气
    0.07
     stationary
    0.07
     scalar
    0.07
    hal
    0.07
     what
    0.06
     FALSE
    0.06
     recher
    0.06
    Act Density 0.041%

    No Known Activations