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

    Neuronpedia

    INDEX
    Explanations

    missing/unknown data

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric literal tokens (especially floating‐point numbers and decimals).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Comet
    -0.07
    -form
    -0.07
    rieg
    -0.07
     Reform
    -0.07
     glove
    -0.06
     medium
    -0.06
    .persist
    -0.06
    crud
    -0.06
     skip
    -0.06
    -stream
    -0.06
    POSITIVE LOGITS
    istar
    0.06
    енным
    0.06
    ॰
    0.06
     يمكن
    0.06
    ires
    0.06
    histoire
    0.06
    .__
    0.06
     gentlemen
    0.06
     retirees
    0.06
    ­
    0.06
    Act Density 0.029%

    No Known Activations