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

    Neuronpedia

    INDEX
    Explanations

    mathematical parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     funz
    1.39
    >());
    1.16
    Diploma
    1.14
     ώστε
    1.14
     corret
    1.11
     использова
    1.10
     помощью
    1.10
    ᴡ
    1.10
     úspě
    1.10
     miso
    1.09
    POSITIVE LOGITS
    koliko
    1.16
    atik
    1.14
    lovers
    1.07
    side
    1.03
    mehr
    1.02
    یت
    0.99
    너무
    0.99
    wikidata
    0.99
    existent
    0.97
    فير
    0.97
    Act Density 0.001%

    No Known Activations