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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the word “equivalent” (especially in the phrase “equivalent to”) in questions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    slideDown
    -0.07
    ados
    -0.07
    _out
    -0.06
     evitar
    -0.06
     excited
    -0.06
     overs
    -0.06
    _dicts
    -0.06
     punches
    -0.06
     soluble
    -0.06
    眼睛
    -0.06
    POSITIVE LOGITS
     arithmetic
    0.07
    ARIANT
    0.06
    ADMIN
    0.06
     име
    0.06
    .cookie
    0.06
    -he
    0.06
     Christine
    0.06
     Nikola
    0.06
     GOODS
    0.06
     getResources
    0.06
    Act Density 0.014%

    No Known Activations