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

    Neuronpedia

    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cerrar
    -0.08
     Cosmos
    -0.07
     proceedings
    -0.07
    ignore
    -0.07
     Names
    -0.06
    사이
    -0.06
    τικο
    -0.06
     procedure
    -0.06
     commemorate
    -0.06
     Production
    -0.06
    POSITIVE LOGITS
     we
    0.09
     they
    0.08
     he
    0.07
     […]...↵
    0.07
     you
    0.07
    'ils
    0.07
     she
    0.07
     it
    0.07
    .%
    0.07
    ULER
    0.06
    Act Density 0.292%

    No Known Activations