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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash

    section and metadata headers that signal Wikipedia/encyclopedia-style article structure

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
     of
    -0.07
     to
    -0.07
     Morning
    -0.06
    abby
    -0.06
    -0.06
     cca
    -0.06
     pInfo
    -0.06
    0
    -0.06
    ыџN
    -0.06
    [axis
    -0.06
    POSITIVE LOGITS
    )↵↵
    0.11
    .↵↵
    0.11
    ​↵↵
    0.11
     //
↵
↵
    0.11
    ↵↵
    0.11
    (){
↵
↵
    0.10
    ).↵↵
    0.10
    )")↵↵
    0.10
    :↵↵
    0.10
    ".↵↵
    0.10
    Act Density 1.241%

    No Known Activations