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

    Neuronpedia

    INDEX
    Explanations

    Foreign Languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    的感情
    -0.07
     recurs
    -0.07
     morning
    -0.07
    视觉
    -0.06
    _DESC
    -0.06
    HEAD
    -0.06
    ǻ
    -0.06
    .layer
    -0.06
     polar
    -0.06
     결국
    -0.06
    POSITIVE LOGITS
     מקצועי
    0.07
     �
    0.07
     '#{
    0.07
     плит
    0.07
    _eff
    0.07
     위한
    0.07
    فيدي
    0.07
    除尘
    0.06
    ᴦ
    0.06
    럭
    0.06
    Act Density 0.000%

    No Known Activations