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

    Neuronpedia

    INDEX
    Explanations

    instances of personal pronouns and their usage in the document

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

    I trying or running

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.52
     betweenstory
    -0.46
    ruptedException
    -0.45
     Biôgrafia
    -0.45
     BoxDecoration
    -0.45
     evergreen
    -0.44
    UnsafeEnabled
    -0.44
    AlterField
    -0.43
    RectangleBorder
    -0.42
    הערות
    -0.42
    POSITIVE LOGITS
    ovým
    0.38
     obtaining
    0.37
     use
    0.36
     usage
    0.36
    Wrong
    0.35
     involving
    0.35
    Identyfik
    0.35
     emple
    0.35
    Use
    0.34
     slicing
    0.34
    Act Density 0.145%

    No Known Activations