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

    Neuronpedia

    INDEX
    Explanations

    easier

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .compile
    -0.07
    itimate
    -0.07
     изготов
    -0.07
     Beit
    -0.07
     trotz
    -0.07
     Киє
    -0.07
     conte
    -0.07
    ()?>
    -0.07
    nilai
    -0.06
    olatile
    -0.06
    POSITIVE LOGITS
     easier
    0.11
     easiest
    0.08
    Within
    0.07
    
    0.07
    虫
    0.07
     �
    0.07
     assist
    0.06
     Toy
    0.06
    easy
    0.06
    -selected
    0.06
    Act Density 0.024%

    No Known Activations