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

    Neuronpedia

    INDEX
    Explanations

    non-specific or generic tokens typically used in coding contexts, such as punctuation marks and formatting characters

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

    legal contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     desmotivaciones
    -0.51
    AsUp
    -0.50
     réalisateur
    -0.47
     Schauspielerin
    -0.42
     cheminée
    -0.41
     Región
    -0.41
    guém
    -0.41
     HFILL
    -0.41
     présidentielle
    -0.41
     combineReducers
    -0.40
    POSITIVE LOGITS
    StoryboardSegue
    0.47
    WriteLiteral
    0.45
    <bos>
    0.45
    EndInit
    0.43
    مراجع
    0.43
    期刊论文
    0.43
    didSet
    0.42
    WindowConstants
    0.41
     Ariz
    0.41
     Widely
    0.41
    Act Density 0.001%

    No Known Activations