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

    Neuronpedia

    INDEX
    Explanations

    then

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Oro
    -0.06
    Shop
    -0.06
    انی
    -0.06
    уди
    -0.06
    uni
    -0.06
     book
    -0.06
     settles
    -0.06
    -к
    -0.06
    ρεια
    -0.06
    _pair
    -0.06
    POSITIVE LOGITS
     ozone
    0.07
     procedure
    0.07
     davran
    0.06
     окра
    0.06
     joked
    0.06
     arşivlendi
    0.06
     ativ
    0.06
     Mixer
    0.06
    _div
    0.06
    .getDescription
    0.06
    Act Density 0.023%

    No Known Activations