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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UPLE
    -0.07
    pcs
    -0.07
     purs
    -0.07
    颂
    -0.07
     ).↵↵
    -0.07
     şikayet
    -0.07
     Millenn
    -0.07
    ']))↵
    -0.07
    我发现
    -0.07
    ARATION
    -0.07
    POSITIVE LOGITS
    띵
    0.08
    �
    0.07
    Interaction
    0.07
    最终
    0.07
    怎么会
    0.07
     interception
    0.07
    (/*
    0.07
     sqlalchemy
    0.07
    見
    0.06
     lombok
    0.06
    Act Density 0.042%

    No Known Activations