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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    院院长
    -0.08
    acio
    -0.07
    ização
    -0.07
    упить
    -0.07
     пол
    -0.07
     работает
    -0.07
     Sell
    -0.07
     capac
    -0.06
     naval
    -0.06
     obrig
    -0.06
    POSITIVE LOGITS
    ⋯
    0.07
    .modal
    0.07
    Uid
    0.06
     bundled
    0.06
     mdl
    0.06
    合作伙伴
    0.06
    uti
    0.06
    txn
    0.06
     SUV
    0.06
    evento
    0.06
    Act Density 0.165%

    No Known Activations