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

    Neuronpedia

    INDEX
    Explanations

    HTML header

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    大多
    -0.07
     BOX
    -0.07
    地域
    -0.07
    均为
    -0.07
     %[
    -0.07
    agonal
    -0.07
     arena
    -0.07
     soci
    -0.06
    よかった
    -0.06
    OLON
    -0.06
    POSITIVE LOGITS
     Eff
    0.07
    Removing
    0.07
    Ң
    0.07
    ഫ
    0.07
     Inhal
    0.07
     jeśli
    0.06
    懔
    0.06
    岂
    0.06
    踏
    0.06
    👸
    0.06
    Act Density 0.146%

    No Known Activations