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

    Neuronpedia

    INDEX
    Explanations

    antonyms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    经
    -0.08
    (range
    -0.07
    browse
    -0.07
    configure
    -0.07
    rowning
    -0.07
     resource
    -0.07
    万名
    -0.07
    INDEX
    -0.07
    &
    -0.07
     nan
    -0.07
    POSITIVE LOGITS
    밨
    0.08
     bearer
    0.07
    olución
    0.07
     שהת
    0.07
    公安局
    0.07
    ação
    0.07
    ستمرار
    0.07
     neutrality
    0.07
     }]
    0.06
    路由器
    0.06
    Act Density 0.009%

    No Known Activations