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

    Neuronpedia

    INDEX
    Explanations

    public class declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /**
    0.49
    ////////////////
    0.40
    ///
    0.39
    ////////////
    0.39
     //</
    0.39
    📂
    0.39
    /////////
    0.38
    Yam
    0.37
     /**
    0.37
    %%%%%%%%%%%%%%%%
    0.37
    POSITIVE LOGITS
     Foo
    0.40
     sida
    0.40
     tid
    0.38
    public
    0.38
    لیت
    0.38
    webdriver
    0.36
     foo
    0.35
    只
    0.35
     Approval
    0.35
    idents
    0.35
    Act Density 0.007%

    No Known Activations