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

    Neuronpedia

    INDEX
    Explanations

    empty attribute

    np_max-act · gemini-2.0-flash

    The neuron is looking for HTML attribute names (like name=, id=, cols=, rows=) inside tag markup.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     TIME
    -0.07
     maritime
    -0.07
     time
    -0.06
     UNITY
    -0.06
     فرو
    -0.06
    ştır
    -0.06
     cows
    -0.06
    thermal
    -0.06
    strate
    -0.06
     Lies
    -0.06
    POSITIVE LOGITS
     Popup
    0.06
     роль
    0.06
    .authService
    0.06
     entreprise
    0.06
    .MoveNext
    0.06
    りと
    0.06
    _dump
    0.06
    _rep
    0.06
    -pointer
    0.05
    _tunnel
    0.05
    Act Density 0.004%

    No Known Activations