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

    Neuronpedia

    INDEX
    Explanations

    instances of specific statistical tests and their results

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

    documents, test

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.91
    AddTagHelper
    -0.84
    AsUp
    -0.76
    OGND
    -0.76
    setVerticalGroup
    -0.76
    UnusedPrivate
    -0.74
     BoxFit
    -0.73
    saraba
    -0.73
     JpaRepository
    -0.73
     $_(
    -0.72
    POSITIVE LOGITS
    AlterField
    1.48
     generally
    0.40
     third
    0.33
     consideran
    0.33
     general
    0.32
     parezca
    0.32
     compared
    0.31
     less
    0.31
     second
    0.31
     
    0.31
    Act Density 0.001%

    No Known Activations