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

    Neuronpedia

    INDEX
    Explanations

    societal issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     you
    -0.10
     You
    -0.08
    You
    -0.07
     they
    -0.07
     YOU
    -0.06
     your
    -0.06
     develops
    -0.06
    They
    -0.06
     yours
    -0.06
    utan
    -0.06
    POSITIVE LOGITS
    џџџ
    0.07
    respuesta
    0.07
    edar
    0.06
    '}↵↵
    0.06
     był
    0.06
     offender
    0.06
     televised
    0.06
    _mag
    0.06
     سید
    0.06
    Toe
    0.06
    Act Density 0.166%

    No Known Activations