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

    Neuronpedia

    INDEX
    Explanations

    words related to legal, political, and moral justifications

    oai_token-act-pair · gemini-2.0-flash

    politics and legal matters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الاطلاع
    -0.77
    RegistryLite
    -0.71
    rrggbb
    -0.69
     referenties
    -0.65
     चीज़ों
    -0.63
    '">
    -0.63
     Familienname
    -0.62
    labelledby
    -0.61
    Népesség
    -0.61
     surla
    -0.59
    POSITIVE LOGITS
     refroid
    0.52
     récomp
    0.49
     fevere
    0.48
     igjen
    0.48
     saludo
    0.46
     testigo
    0.46
     vettor
    0.45
    oara
    0.45
    ="#"><
    0.45
     ſever
    0.44
    Act Density 5.454%

    No Known Activations