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

    Neuronpedia

    INDEX
    Explanations

    descriptions

    np_max-act · gemini-2.0-flash

    This neuron activates primarily on past-tense or past-participial words ending in “-ed.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    HostException
    -0.07
    sigma
    -0.06
    _sizes
    -0.06
    рал
    -0.06
    (D
    -0.06
    SPAN
    -0.06
     Roy
    -0.06
    iphers
    -0.06
     درجه
    -0.06
    โน
    -0.06
    POSITIVE LOGITS
    σσότε
    0.07
    _csv
    0.06
    š
    0.06
    ā
    0.06
     Bulg
    0.06
    又
    0.06
    .lineTo
    0.06
    esion
    0.06
     broadly
    0.06
    개월
    0.06
    Act Density 0.157%

    No Known Activations