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

    Neuronpedia

    INDEX
    Explanations

    quality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     classifications
    -0.07
    ceeded
    -0.07
     shores
    -0.07
    idd
    -0.07
    ariance
    -0.07
    erging
    -0.06
    ners
    -0.06
    Stats
    -0.06
     seven
    -0.06
     partic
    -0.06
    POSITIVE LOGITS
    apy
    0.07
     gy
    0.06
     hazır
    0.06
    <pair
    0.06
     Amy
    0.06
    Ky
    0.06
    .every
    0.06
    .onCreate
    0.06
     оди
    0.06
     castle
    0.06
    Act Density 0.008%

    No Known Activations