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

    Neuronpedia

    INDEX
    Explanations

    update

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _numero
    -0.07
     («
    -0.06
    uae
    -0.06
    WE
    -0.06
    ль
    -0.06
     AUT
    -0.06
     Camera
    -0.06
    chestra
    -0.06
    爭
    -0.06
     имп
    -0.06
    POSITIVE LOGITS
    Ensure
    0.08
     updates
    0.07
     updating
    0.07
    Updates
    0.07
     Ensure
    0.07
    kb
    0.07
    Ordered
    0.07
     useless
    0.06
     Updates
    0.06
    .chunk
    0.06
    Act Density 0.009%

    No Known Activations