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

    Neuronpedia

    INDEX
    Explanations

    possessive/contraction "is"

    np_max-act · gemini-2.0-flash

    The neuron activates on deictic assertion phrases—specifically instances of “That’s …” or “This is …” at the start of a statement.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Epoch
    -0.07
    TRA
    -0.07
    807
    -0.07
    _SKIP
    -0.06
    kov
    -0.06
     Print
    -0.06
    Foo
    -0.06
     guided
    -0.06
    Scalar
    -0.06
    &a
    -0.06
    POSITIVE LOGITS
    …↵↵
    0.06
     свого
    0.06
     Його
    0.06
     labels
    0.06
    ReturnValue
    0.06
    createQueryBuilder
    0.06
    (equalTo
    0.06
     greatest
    0.06
     เวลา
    0.06
     everytime
    0.06
    Act Density 0.028%

    No Known Activations