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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens—especially floating‐point or decimal numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     />,↵
    -0.07
    ilan
    -0.07
    .Send
    -0.06
    ตรวจ
    -0.06
    Plugins
    -0.06
     letters
    -0.06
     volunteering
    -0.06
    akov
    -0.06
     contestant
    -0.06
     [,
    -0.06
    POSITIVE LOGITS
     imageNamed
    0.07
     Ce
    0.06
    لي
    0.06
    semble
    0.06
     scramble
    0.06
    Beauty
    0.06
     Plum
    0.06
    pun
    0.06
    ласти
    0.06
    �
    0.06
    Act Density 0.005%

    No Known Activations