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

    Neuronpedia

    INDEX
    Explanations

    math questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     barrels
    -0.07
    .parse
    -0.07
    ynamic
    -0.07
    ILD
    -0.06
    DOC
    -0.06
     lamps
    -0.06
    -guard
    -0.06
    sqrt
    -0.06
    398
    -0.06
    BMI
    -0.06
    POSITIVE LOGITS
    -с
    0.06
     сама
    0.06
     onay
    0.06
    ReuseIdentifier
    0.06
     hoy
    0.06
     teor
    0.06
     앉
    0.06
     есте
    0.06
     nghiệp
    0.06
     onView
    0.05
    Act Density 0.049%

    No Known Activations