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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens that are numeric values—especially decimal numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    �
    -0.07
     submissive
    -0.06
     Elves
    -0.06
     Grants
    -0.06
    <Node
    -0.06
    ls
    -0.06
    489
    -0.06
    newsletter
    -0.06
     Richards
    -0.06
    네
    -0.06
    POSITIVE LOGITS
     }));↵↵
    0.07
     futuro
    0.07
    ToInt
    0.07
    ουν
    0.07
     sor
    0.07
     повтор
    0.06
    "],
    0.06
     investigating
    0.06
    .engine
    0.06
    coil
    0.06
    Act Density 0.015%

    No Known Activations