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

    Neuronpedia

    INDEX
    Explanations

    conversational prompts and questions

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

    Follows "A:" in a conversation

    np_acts-logits-general · gemini-2.0-flash

    Based on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InstrumentedTest
    -0.56
    AndEndTag
    -0.52
    xase
    -0.51
    webElementXpaths
    -0.51
    ніципа
    -0.48
    WebElementEntity
    -0.47
     EconPapers
    -0.46
    IntoConstraints
    -0.45
     disambiguazione
    -0.44
     nahilalakip
    -0.42
    POSITIVE LOGITS
     Vikipedi
    0.42
    gesamt
    0.42
    engg
    0.41
    setC
    0.41
     holl
    0.41
    躇
    0.40
     MEN
    0.40
    last
    0.40
    MEN
    0.40
    Enigma
    0.40
    Act Density 0.083%

    No Known Activations