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

    Neuronpedia

    INDEX
    Explanations

    spa treatments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ग
    -0.07
    Plane
    -0.07
     Бол
    -0.06
    gue
    -0.06
     wish
    -0.06
    (mp
    -0.06
     supermarket
    -0.06
    oba
    -0.06
    ITY
    -0.06
    (Chat
    -0.06
    POSITIVE LOGITS
     obce
    0.07
     bleibt
    0.07
     ά
    0.07
     uncert
    0.06
    .Remove
    0.06
     Vanderbilt
    0.06
     Manafort
    0.06
     Clothing
    0.06
    creation
    0.06
    …↵↵
    0.06
    Act Density 0.127%

    No Known Activations