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

    Neuronpedia

    INDEX
    Explanations

    "<"

    np_max-act · gemini-2.0-flash

    The neuron is triggered by the “<” token marking the start of an HTML tag.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    classmethod
    -0.07
    ora
    -0.07
     Gavin
    -0.07
    (encoder
    -0.07
    special
    -0.07
    (cors
    -0.07
    acak
    -0.06
     Merk
    -0.06
    율
    -0.06
    wizard
    -0.06
    POSITIVE LOGITS
     acquisition
    0.07
     Acquisition
    0.06
    _the
    0.06
    .ActionEvent
    0.06
    auses
    0.06
    <Any
    0.06
     rake
    0.06
     unreasonable
    0.06
     الحر
    0.06
     Skills
    0.05
    Act Density 0.003%

    No Known Activations