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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    à
    -0.08
    oir
    -0.07
     Jack
    -0.07
    发布时间
    -0.06
     CTRL
    -0.06
    UILT
    -0.06
     Math
    -0.06
     conversion
    -0.06
    ù
    -0.06
     đồng
    -0.06
    POSITIVE LOGITS
    ))):↵
    0.07
    >());↵↵
    0.07
     scenes
    0.07
    ...(
    0.06
    thumbnails
    0.06
    );
↵
↵
↵
    0.06
     sneakers
    0.06
    殖民
    0.06
     ceremon
    0.06
    ]}</
    0.06
    Act Density 0.012%

    No Known Activations