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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash

    The neuron fires on HTML form “name” attributes (particularly on input elements’ name= tokens).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    METHOD
    -0.07
    .abort
    -0.06
    _MODE
    -0.06
    arrant
    -0.06
    CEL
    -0.06
     Conversion
    -0.06
     січ
    -0.06
    cers
    -0.06
     Result
    -0.06
    ategies
    -0.06
    POSITIVE LOGITS
     gü
    0.07
     đi
    0.07
     beim
    0.07
    라
    0.07
     wäre
    0.06
     нельзя
    0.06
    newInstance
    0.06
    [msg
    0.06
    licher
    0.06
    `(
    0.06
    Act Density 0.002%

    No Known Activations