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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sizes
    -0.07
     centers
    -0.06
     Kay
    -0.06
    fluid
    -0.06
     partisan
    -0.06
    Ｏ
    -0.06
    ASF
    -0.06
    longitude
    -0.06
    /Form
    -0.06
    close
    -0.06
    POSITIVE LOGITS
    식을
    0.07
     سپس
    0.07
     الناس
    0.06
    воля
    0.06
     hastalık
    0.06
     리그
    0.06
     kendini
    0.06
    ंगल
    0.06
    ΙΚΗ
    0.06
    чили
    0.06
    Act Density 0.067%

    No Known Activations