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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aneous
    -0.08
    뜻
    -0.07
     위원님
    -0.07
     неск
    -0.07
     międzynar
    -0.07
    حفاظ
    -0.07
    虼
    -0.07
    万平方米
    -0.07
    희
    -0.07
    ex
    -0.06
    POSITIVE LOGITS
    DRAM
    0.10
    (rad
    0.08
     flowering
    0.07
     Ram
    0.07
     Pad
    0.07
     Colts
    0.07
    ________
    0.07
    .Country
    0.07
    alam
    0.07
     tart
    0.07
    Act Density 0.070%

    No Known Activations