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

    Neuronpedia

    INDEX
    Explanations

    Tuning (instruments)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exer
    -0.08
    ouncement
    -0.08
    లన
    -0.08
     الالت
    -0.08
    edor
    -0.07
     നടത്തിയ
    -0.07
     squeezing
    -0.07
     بشأن
    -0.07
    告
    -0.07
     infringement
    -0.07
    POSITIVE LOGITS
     Mole
    0.08
     lengkap
    0.08
     магазин
    0.08
     terdiri
    0.08
    옥
    0.08
     hybride
    0.08
     befest
    0.07
     tradicionais
    0.07
     Hex
    0.07
     tradicional
    0.07
    Act Density 0.004%

    No Known Activations