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

    Neuronpedia

    INDEX
    Explanations

    syntactic structures and formatting elements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Equality and inequality comparisons

    np_acts-logits-general · gemini-2.0-flash

    code assignment and comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     al
    -0.57
    upra
    -0.47
     duras
    -0.45
    <eos>
    -0.42
    rod
    -0.41
    GeneratedCode
    -0.41
     sub
    -0.41
     but
    -0.40
    olan
    -0.39
    parseFrom
    -0.39
    POSITIVE LOGITS
    IntoConstraints
    1.08
    ."</
    0.93
     Normdatei
    0.86
    AddTagHelper
    0.86
    bootstrapcdn
    0.83
    ChildScrollView
    0.83
     }}"></
    0.82
    __":
    0.80
     تضيفلها
    0.78
    ")));
    0.77
    Act Density 0.368%

    No Known Activations