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

    Neuronpedia

    INDEX
    Explanations

    where

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens—especially standalone numbers or numeric literals (e.g. integers and decimals).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ROUGH
    -0.08
    олее
    -0.07
    нос
    -0.07
    athed
    -0.06
    认
    -0.06
    rowable
    -0.06
    vá
    -0.06
    苏
    -0.06
    .assertj
    -0.06
    ailability
    -0.06
    POSITIVE LOGITS
     competitor
    0.07
     จำก
    0.06
     creatures
    0.06
    /*↵↵
    0.06
    Emma
    0.06
    Remarks
    0.06
     introducing
    0.06
    '));↵↵
    0.06
    諸
    0.06
     oxidation
    0.06
    Act Density 0.006%

    No Known Activations