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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     layers
    -0.08
     é
    -0.08
     tobacco
    -0.07
    发现
    -0.07
    也是
    -0.07
    plers
    -0.07
     Layers
    -0.07
    NOP
    -0.07
     Tobacco
    -0.07
     Nich
    -0.07
    POSITIVE LOGITS
     razo
    0.09
     పేరు
    0.09
     spaceship
    0.08
     fname
    0.08
     ಹೆಸರು
    0.08
     tevoren
    0.08
     william
    0.08
    0.08
    0.08
    ">'
    0.08
    Act Density 0.008%
    No Known Activations