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

    Neuronpedia

    INDEX
    Explanations

    /* comments and code block keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    **/
    0.46
    :**
    0.41
     **/
    0.40
    **.
    0.40
    体验
    0.39
     страницы
    0.38
     vitt
    0.38
    ³/
    0.38
    ori
    0.38
    尧
    0.38
    POSITIVE LOGITS
    /*
    0.75
     /*
    0.59
     renamed
    0.58
    ,/*
    0.48
     {/*
    0.47
     anonymous
    0.46
     anonymously
    0.45
    /*'
    0.44
     anonym
    0.44
    <em>
    0.44
    Act Density 0.000%

    No Known Activations