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

    Neuronpedia

    INDEX
    Explanations

    within

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -u
    -0.07
    �
    -0.07
    企業
    -0.06
     thay
    -0.06
    Dep
    -0.06
    utor
    -0.06
    ق
    -0.06
    -money
    -0.06
     flipped
    -0.06
     babes
    -0.06
    POSITIVE LOGITS
     utrecht
    0.07
     NK
    0.07
     základní
    0.07
     histoire
    0.07
     jednotlivých
    0.07
     Supplementary
    0.06
     autour
    0.06
    .attr
    0.06
     Воз
    0.06
    σταση
    0.06
    Act Density 0.014%

    No Known Activations