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

    Neuronpedia

    INDEX
    Explanations

    policy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .each
    -0.07
    做的事
    -0.07
    Dispatch
    -0.07
     Perl
    -0.06
    投入使用
    -0.06
    Independ
    -0.06
     mortality
    -0.06
    isposable
    -0.06
    _pci
    -0.06
    MainThread
    -0.06
    POSITIVE LOGITS
    莩
    0.08
    /blue
    0.07
     multinational
    0.07
     bols
    0.07
    probante
    0.07
    ի
    0.07
    грамм
    0.07
     prostitutas
    0.07
    赤ちゃん
    0.07
    basket
    0.07
    Act Density 0.011%

    No Known Activations