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

    Neuronpedia

    INDEX
    Explanations

    results

    np_max-act · gemini-2.0-flash

    The neuron activates on floating‐point numeric values (e.g., decimal statistics or measurements) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    contracts
    -0.08
     Zimmer
    -0.07
     coolant
    -0.06
    *=
    -0.06
     rever
    -0.06
     belt
    -0.06
    "H
    -0.06
     contracts
    -0.06
     jika
    -0.06
    anteed
    -0.06
    POSITIVE LOGITS
    َك
    0.07
    äll
    0.07
     Marin
    0.06
    igure
    0.06
    /plain
    0.06
    ك
    0.06
    独
    0.06
     Spice
    0.06
    .BASE
    0.06
     Stick
    0.06
    Act Density 0.035%

    No Known Activations