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

    Neuronpedia

    INDEX
    Explanations

    of about

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reacts
    -0.08
    _CAPACITY
    -0.07
     Jian
    -0.06
     Give
    -0.06
    select
    -0.06
     Therefore
    -0.06
     Josef
    -0.06
     elephants
    -0.06
     didnt
    -0.06
     Panel
    -0.06
    POSITIVE LOGITS
    ุค
    0.07
    양
    0.06
    _reserve
    0.06
     unsure
    0.06
     मल
    0.06
    /↵↵↵
    0.06
     intellectuals
    0.06
    .NO
    0.06
    察
    0.06
    年龄
    0.06
    Act Density 0.013%

    No Known Activations