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

    Neuronpedia

    INDEX
    Explanations

    instances of negation or contradiction in statements

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

    conjunctions and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.45
     GenerationType
    -0.43
    expandindo
    -0.40
     occupies
    -0.39
     oka
    -0.38
    InstrumentedTest
    -0.38
    نش
    -0.37
     نش
    -0.37
    Fourth
    -0.37
    ➟
    -0.36
    POSITIVE LOGITS
    SharedCtor
    0.53
    guisement
    0.45
    VIAF
    0.42
     <=",
    0.42
    uvwxyz
    0.41
     bolsillos
    0.41
     tatuagens
    0.41
     âmes
    0.40
    akaan
    0.39
    tahankan
    0.39
    Act Density 0.133%

    No Known Activations