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

    Neuronpedia

    INDEX
    Explanations

    comparative, ending in "er"

    np_max-act · gemini-2.0-flash

    The neuron activates on comparative adjectives (words in the "-er" form).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    藝
    -0.07
    will
    -0.07
     obtained
    -0.07
    v
    -0.07
    bout
    -0.07
     onView
    -0.07
    would
    -0.06
    ับ
    -0.06
    ill
    -0.06
    ould
    -0.06
    POSITIVE LOGITS
     stronger
    0.12
     wider
    0.12
    Higher
    0.12
     larger
    0.12
     faster
    0.12
    er
    0.12
    ER
    0.12
     harder
    0.12
     higher
    0.11
     Faster
    0.11
    Act Density 0.101%

    No Known Activations