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

    Neuronpedia

    INDEX
    Explanations

    mouse

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect numeric tokens (especially decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ID
    -0.07
     experts
    -0.07
     ==========
    -0.07
    changing
    -0.07
    uing
    -0.06
     Dit
    -0.06
    ammo
    -0.06
    JC
    -0.06
    „To
    -0.06
     заходів
    -0.06
    POSITIVE LOGITS
     vũ
    0.06
     Donetsk
    0.06
     Böyle
    0.06
     Leipzig
    0.06
    staw
    0.06
    .showMessage
    0.06
     Evans
    0.06
    لی
    0.06
     propagation
    0.06
     Guzzle
    0.06
    Act Density 0.561%

    No Known Activations