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

    Neuronpedia

    INDEX
    Explanations

    Karl

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    买了
    -0.07
    ปลา
    -0.07
    原件
    -0.07
     телефон
    -0.07
     nice
    -0.07
    청소
    -0.07
     настоя
    -0.07
     OUT
    -0.07
     titten
    -0.07
    7
    -0.07
    POSITIVE LOGITS
     withdrawal
    0.07
    индивидуальн
    0.07
    можем
    0.07
     onCancelled
    0.07
    .hasClass
    0.07
     persuaded
    0.07
     iVar
    0.06
     ITS
    0.06
    并非
    0.06
    HandlerContext
    0.06
    Act Density 0.046%

    No Known Activations