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

    Neuronpedia

    INDEX
    Explanations

    ordinal numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    place
    -0.07
    Place
    -0.07
    oss
    -0.07
    頭
    -0.07
    Woman
    -0.07
    �
    -0.06
    loggedIn
    -0.06
     twig
    -0.06
    erin
    -0.06
    -cal
    -0.06
    POSITIVE LOGITS
     имеют
    0.07
    CCCC
    0.07
     currentValue
    0.06
     willen
    0.06
     underworld
    0.06
     العربية
    0.06
     jeder
    0.06
     Dek
    0.06
     fruitful
    0.06
     cumulative
    0.06
    Act Density 0.004%

    No Known Activations