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

    Neuronpedia

    INDEX
    Explanations

    follow

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sel
    -0.08
     browse
    -0.07
     тоже
    -0.07
     pension
    -0.07
     Fiesta
    -0.07
    _buy
    -0.07
    涨价
    -0.07
     migrant
    -0.07
     tasted
    -0.07
    油耗
    -0.07
    POSITIVE LOGITS
    之情
    0.07
    others
    0.07
     Kumar
    0.07
    uya
    0.06
    n
    0.06
    umar
    0.06
    Activity
    0.06
     común
    0.06
    𝑅
    0.06
     andra
    0.06
    Act Density 0.040%

    No Known Activations