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

    Neuronpedia

    INDEX
    Explanations

    php code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     INTEGER
    0.39
     fclose
    0.38
    もり
    0.37
    を起こ
    0.36
     మరి
    0.36
    вате
    0.35
     Sas
    0.35
     integer
    0.35
     FK
    0.35
     Kondo
    0.35
    POSITIVE LOGITS
    function
    0.61
     function
    0.57
    Abstract
    0.53
     abstracts
    0.53
    class
    0.52
    abstract
    0.50
     Funktion
    0.47
     fonction
    0.46
    抽象
    0.46
     फंक्शन
    0.46
    Act Density 0.001%

    No Known Activations