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

    Neuronpedia

    INDEX
    Explanations

    math calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     відб
    -0.07
     throughput
    -0.07
    ovými
    -0.07
     enrol
    -0.07
     equalTo
    -0.07
     thuận
    -0.07
     stencil
    -0.07
    flex
    -0.07
    departure
    -0.06
     exem
    -0.06
    POSITIVE LOGITS
     Sunrise
    0.06
    :white
    0.06
    rent
    0.05
     जग
    0.05
    소
    0.05
    thane
    0.05
    �始化
    0.05
    _duration
    0.05
     recognized
    0.05
     rid
    0.05
    Act Density 0.018%

    No Known Activations