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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicative of legal arguments and evidence

    oai_token-act-pair · gemini-2.0-flash

    legal proceedings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Становништво
    -0.87
     magnitude
    -0.72
    Magnitude
    -0.70
     Magnitude
    -0.70
     Extent
    -0.68
    magnitude
    -0.67
    extent
    -0.64
     مرئيه
    -0.64
     size
    -0.64
     فريبيس
    -0.64
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.49
    Carriera
    0.47
     gelieb
    0.47
    ंदीखरीदारी
    0.47
    IVEREF
    0.47
    Rptr
    0.46
    ğinde
    0.45
     biji
    0.45
     zonal
    0.44
    sses
    0.44
    Act Density 10.204%

    No Known Activations