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

    Neuronpedia

    INDEX
    Explanations

    game mechanics and difficulty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ful
    -0.08
     Cay
    -0.08
    办理
    -0.08
    -0.07
     beslut
    -0.07
     oração
    -0.07
     devotional
    -0.07
     تمام
    -0.07
    uyi
    -0.07
    irth
    -0.07
    POSITIVE LOGITS
     aumentando
    0.13
    ifficulty
    0.13
    difficulty
    0.12
     progressively
    0.12
     Increasing
    0.12
    Difficulty
    0.12
     difficulty
    0.12
     increasing
    0.12
     Difficulty
    0.11
     harder
    0.11
    Act Density 0.008%
    No Known Activations