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

    Neuronpedia

    INDEX
    Explanations

    Code/software/scripts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     night
    -0.27
    æ·ĺæ±°
    -0.26
    hibit
    -0.26
     nighttime
    -0.25
     moderne
    -0.25
    ursor
    -0.24
     Rocket
    -0.24
    è°ĪæģĭçĪ±
    -0.24
    aket
    -0.24
    :test
    -0.24
    POSITIVE LOGITS
    顾
    0.27
    "+"
    0.25
     schem
    0.25
    åIJĮäºĭ们
    0.24
    lässig
    0.24
    åĽłç´ł
    0.24
    epad
    0.24
    lest
    0.24
    åĬ¡å®ŀ
    0.23
    é¦
    0.23
    Act Density 0.002%

    No Known Activations