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

    Neuronpedia

    INDEX
    Explanations

    questions and conjectures related to actions and possibilities

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

    what questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    JspWriter
    -0.67
     nakalista
    -0.62
    FieldBuilder
    -0.62
     Exacts
    -0.60
    +:+
    -0.60
    PropertyChanging
    -0.56
    TagMode
    -0.56
    oredCriteria
    -0.56
    AddTagHelper
    -0.56
    SharedCtor
    -0.55
    POSITIVE LOGITS
     what
    0.77
    what
    0.65
     What
    0.62
    What
    0.60
     WHAT
    0.58
    WHAT
    0.46
    IANGLES
    0.42
    assertEqual
    0.38
    干什么
    0.38
    fclose
    0.37
    Act Density 0.014%

    No Known Activations