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

    Neuronpedia

    INDEX
    Explanations

    dates, numbers

    np_max-act · gemini-2.0-flash

    The neuron detects version numbers and associated release dates in changelog entries.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    >Status
    -0.06
    佛
    -0.06
     dbg
    -0.06
    受到
    -0.06
     bearings
    -0.06
     luggage
    -0.06
     testcase
    -0.06
     ]);↵↵
    -0.06
     strSQL
    -0.06
     chaotic
    -0.06
    POSITIVE LOGITS
     �
    0.07
    เปอร
    0.06
    гар
    0.06
    invest
    0.06
    IV
    0.06
     Vol
    0.06
     Geme
    0.06
     Česk
    0.06
     Creed
    0.06
    .top
    0.06
    Act Density 0.003%

    No Known Activations