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

    Neuronpedia

    INDEX
    Explanations

    ach

    np_max-act · gemini-2.0-flash

    This neuron detects capitalized proper names, especially company/product or organization names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     wind
    -0.07
    =(-
    -0.07
     intrigued
    -0.06
     duo
    -0.06
     vũ
    -0.06
     územ
    -0.06
     nederland
    -0.06
    .publish
    -0.06
    _COLOR
    -0.06
    .Axis
    -0.06
    POSITIVE LOGITS
    }
↵
↵
↵
    0.07
    plants
    0.07
    _An
    0.06
    iế
    0.06
     shutting
    0.06
     ступ
    0.06
     ниж
    0.06
     Officers
    0.06
    iesen
    0.06
     Officer
    0.06
    Act Density 0.313%

    No Known Activations