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

    Neuronpedia

    INDEX
    Explanations

    which one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bella
    -0.08
    .define
    -0.07
     fantastische
    -0.07
     ~/.
    -0.07
    .Default
    -0.07
    irme
    -0.07
    '],
    -0.07
    .yaml
    -0.07
    .Config
    -0.07
    prowadz
    -0.07
    POSITIVE LOGITS
    哪个
    0.09
     dentre
    0.09
     الوحيد
    0.08
     phù
    0.08
    lerden
    0.08
     наиболее
    0.08
     memenuhi
    0.08
     dintre
    0.08
     aanbieding
    0.08
     sew
    0.08
    Act Density 0.027%

    No Known Activations