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

    Neuronpedia

    INDEX
    Explanations

    code/urls

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [user
    -0.07
    最多
    -0.07
    _req
    -0.07
     blaze
    -0.07
     Px
    -0.07
     processor
    -0.07
    people
    -0.06
    _op
    -0.06
    _dialog
    -0.06
    -ajax
    -0.06
    POSITIVE LOGITS
    迴
    0.08
     !↵
    0.07
    表现为
    0.07
    巡回
    0.07
    続いて
    0.07
     ';↵
    0.07
    );}↵
    0.07
    ')}↵
    0.07
    ]]↵
    0.07
    arf
    0.07
    Act Density 0.013%

    No Known Activations