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

    Neuronpedia

    INDEX
    Explanations

    מ

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kro
    -0.06
     hızlı
    -0.06
     іншого
    -0.06
     hotter
    -0.06
     plac
    -0.06
    (circle
    -0.06
    Whole
    -0.06
     Пло
    -0.06
     Std
    -0.06
     wholes
    -0.06
    POSITIVE LOGITS
     help
    0.07
    _region
    0.07
     Bordeaux
    0.07
     vig
    0.06
    انية
    0.06
    λι
    0.06
    间
    0.06
    ajan
    0.06
    .ul
    0.06
     vita
    0.06
    Act Density 0.004%

    No Known Activations