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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    将迎来
    -0.06
     января
    -0.06
    怎
    -0.06
     сентября
    -0.06
     trustees
    -0.06
    听
    -0.06
     […
    -0.06
    President
    -0.06
    TeX
    -0.06
    经验丰富
    -0.06
    POSITIVE LOGITS
    coholic
    0.08
     flights
    0.08
     battled
    0.07
    flo
    0.07
     regulatory
    0.07
     polic
    0.07
    @Table
    0.07
    .Side
    0.07
    _war
    0.07
     były
    0.07
    Act Density 0.049%

    No Known Activations