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

    Neuronpedia

    INDEX
    Explanations

    Resolver

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     power
    -0.07
     Stop
    -0.07
     mutate
    -0.07
    ripp
    -0.07
    开放
    -0.06
    -operation
    -0.06
    timezone
    -0.06
    Outdoor
    -0.06
     popover
    -0.06
    鲯
    -0.06
    POSITIVE LOGITS
     dealer
    0.08
    _models
    0.07
    等行业
    0.07
     stakes
    0.07
     비교
    0.07
     حسين
    0.07
    开发商
    0.07
     Archer
    0.07
     @$
    0.06
    的研究
    0.06
    Act Density 0.002%

    No Known Activations