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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash

    This neuron detects the preposition “at,” as used to link people with institutions or events.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    returns
    -0.07
     alguns
    -0.07
    Geometry
    -0.06
     semanas
    -0.06
    _Find
    -0.06
    -but
    -0.06
     Teil
    -0.06
    retrieve
    -0.06
     самой
    -0.06
     kiểu
    -0.06
    POSITIVE LOGITS
     Conservation
    0.07
     appropri
    0.07
     ND
    0.07
     AT
    0.07
    482
    0.07
    .Gen
    0.07
    WC
    0.07
    row
    0.06
     wall
    0.06
    .Clone
    0.06
    Act Density 0.030%

    No Known Activations