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

    Neuronpedia

    INDEX
    Explanations

    entitled

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aangezien
    -0.08
     calibration
    -0.08
     sie
    -0.07
    serial
    -0.07
    armon
    -0.07
    unity
    -0.07
     נע
    -0.07
     teuer
    -0.07
     calibrated
    -0.07
     že
    -0.07
    POSITIVE LOGITS
     अधिकार
    0.11
     rights
    0.10
    权益
    0.10
     Rights
    0.09
     direitos
    0.09
     주장
    0.09
    待遇
    0.09
     grievance
    0.09
    rights
    0.09
     grievances
    0.08
    Act Density 0.040%

    No Known Activations