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

    Neuronpedia

    INDEX
    Explanations

    Un

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tiger
    -0.07
     Andreas
    -0.06
    Dimension
    -0.06
     durability
    -0.06
    渐
    -0.06
    ęki
    -0.06
     آموز
    -0.06
     ankle
    -0.06
    inosaur
    -0.06
     literally
    -0.06
    POSITIVE LOGITS
    '];↵
    0.07
    >';↵
    0.07
    SAT
    0.07
    .uni
    0.07
    /sys
    0.07
    UN
    0.07
    >');↵
    0.06
    ";↵
    0.06
    ]',↵
    0.06
     //{↵
    0.06
    Act Density 0.023%

    No Known Activations