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

    Neuronpedia

    INDEX
    Explanations

    head and headwear

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     powertrain
    0.53
     plasmids
    0.50
     vetting
    0.50
     sofas
    0.48
     fintech
    0.48
     shortfall
    0.48
     leasing
    0.47
     copywriting
    0.47
     offshoring
    0.46
     योग्यता
    0.46
    POSITIVE LOGITS
     headband
    1.00
    头
    1.00
     forehead
    0.98
     head
    0.96
     helmet
    0.95
     Head
    0.88
     頭
    0.87
     roof
    0.86
     头
    0.85
     머
    0.83
    Act Density 0.201%

    No Known Activations