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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    報告
    -0.07
    บาง
    -0.06
    ◐
    -0.06
     Pence
    -0.06
     interception
    -0.06
     scenarios
    -0.06
     práctica
    -0.06
     accounting
    -0.06
    reported
    -0.06
     Sens
    -0.06
    POSITIVE LOGITS
    做过
    0.07
    .off
    0.06
     król
    0.06
    听了
    0.06
    lda
    0.06
     stiff
    0.06
    М
    0.06
    olygon
    0.06
    });↵
    0.06
     Она
    0.06
    Act Density 0.117%

    No Known Activations