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

    Neuronpedia

    INDEX
    Explanations

    div

    np_max-act · gemini-2.0-flash

    This neuron detects HTML “div” tag tokens (i.e. the occurrences of `<div>` and related closing-tag tokens).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ีโ
    -0.07
    perature
    -0.07
    LT
    -0.06
    .resume
    -0.06
    Diagram
    -0.06
    ateria
    -0.06
     Quarter
    -0.06
    85
    -0.06
    Supplier
    -0.06
    imator
    -0.06
    POSITIVE LOGITS
     ged
    0.07
    -st
    0.07
     perce
    0.06
     fright
    0.06
    sic
    0.06
    ←
    0.06
     메
    0.06
    นค
    0.06
     kans
    0.06
    $http
    0.06
    Act Density 0.016%

    No Known Activations