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

    Neuronpedia

    INDEX
    Explanations

    solving word problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    字体
    -0.09
     fleur
    -0.09
    旗下
    -0.09
     feta
    -0.08
     aesthetic
    -0.08
     사용하는
    -0.08
     hemp
    -0.08
     transforming
    -0.08
    艳
    -0.08
     fermented
    -0.08
    POSITIVE LOGITS
     stopwatch
    0.13
     timings
    0.12
    _delay
    0.12
    .timeline
    0.12
    Arrival
    0.12
     arrivals
    0.12
     durations
    0.12
    _wait
    0.12
     Waiting
    0.12
    Waiting
    0.12
    Act Density 0.063%

    No Known Activations