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

    Neuronpedia

    INDEX
    Explanations

    image generation instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    reverse
    -0.08
     Toe
    -0.08
     ((((
    -0.08
     reverse
    -0.08
     ular
    -0.08
     Reverse
    -0.07
    tog
    -0.07
    mast
    -0.07
     asfalt
    -0.07
     enjoyment
    -0.07
    POSITIVE LOGITS
    ственная
    0.09
    omy
    0.09
    ственной
    0.08
     tətbi
    0.08
    ワ
    0.07
    лай
    0.07
    ственную
    0.07
     watts
    0.07
     ワ
    0.07
    ministerium
    0.07
    Act Density 0.002%

    No Known Activations