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

    Neuronpedia

    INDEX
    Explanations

    tech forums

    np_max-act · gemini-2.0-flash

    The neuron is a detector for positive evaluative words—praise, recommendation, or enthusiastic sentiment.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     February
    -0.07
    
    -0.07
     iyileş
    -0.07
     Stockholm
    -0.07
     Мор
    -0.06
    adin
    -0.06
    uels
    -0.06
     h
    -0.06
    р
    -0.06
     Cli
    -0.06
    POSITIVE LOGITS
    лаг
    0.07
    Voltage
    0.06
    ้าก
    0.06
    елеф
    0.06
    eyes
    0.06
    <path
    0.06
    estado
    0.06
    +xml
    0.06
    	table
    0.06
    /Page
    0.06
    Act Density 0.029%

    No Known Activations