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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    This neuron detects the infinitive phrase “made … to be,” i.e. the sequence “made” + “to” + “be.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    continuous
    -0.07
    elaide
    -0.07
     Pais
    -0.06
     нев
    -0.06
    антаж
    -0.06
     reckless
    -0.06
     NES
    -0.06
    ってる
    -0.06
    Semantic
    -0.06
    (gen
    -0.06
    POSITIVE LOGITS
     poder
    0.07
     caravan
    0.07
     widow
    0.07
     všem
    0.06
     vitamins
    0.06
    ahoma
    0.06
     optionally
    0.06
     등의
    0.06
    UNIT
    0.06
     уровне
    0.06
    Act Density 0.050%

    No Known Activations