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

    Neuronpedia

    INDEX
    Explanations

    Names of people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Delta
    -0.07
    ades
    -0.07
     Kaz
    -0.07
     Pais
    -0.07
    Naz
    -0.07
     Lumpur
    -0.07
    ωμα
    -0.07
     Polar
    -0.06
     mah
    -0.06
     Miss
    -0.06
    POSITIVE LOGITS
    _INTERNAL
    0.07
    sprite
    0.07
    우
    0.06
    dre
    0.06
    drv
    0.06
    _EXPR
    0.06
     verifier
    0.06
    edback
    0.06
     производства
    0.06
     dividend
    0.06
    Act Density 0.023%

    No Known Activations