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

    Neuronpedia

    INDEX
    Explanations

    ordering and retransmission

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    階段
    -0.07
    吕
    -0.06
    諮
    -0.06
    _ter
    -0.06
    _epochs
    -0.06
     öff
    -0.06
    婤
    -0.06
     Cascade
    -0.06
    넌
    -0.06
    检测
    -0.06
    POSITIVE LOGITS
    轫
    0.07
    ListModel
    0.07
    atemala
    0.07
     committees
    0.07
     humble
    0.07
    IGIN
    0.07
     boasted
    0.07
     vitamin
    0.06
    tracts
    0.06
    婻
    0.06
    Act Density 0.031%

    No Known Activations