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

    Neuronpedia

    INDEX
    Explanations

    cost or price

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     loads
    0.71
    🏝
    0.71
     dense
    0.69
     aumentada
    0.66
     друг
    0.66
     Bubble
    0.65
     denser
    0.65
     gather
    0.64
     abundant
    0.64
     Fl
    0.64
    POSITIVE LOGITS
     value
    2.21
    value
    2.13
     Value
    1.95
     price
    1.88
    Value
    1.83
    price
    1.75
    VALUE
    1.70
     VALUE
    1.69
     cost
    1.66
    价值
    1.63
    Act Density 0.294%

    No Known Activations