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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and symbols, as well as phrases indicating legal or regulatory language

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

    preserving surjection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SerializedSize
    -0.54
    verifyException
    -0.48
    expandindo
    -0.48
    Derbyniad
    -0.47
    Diweddarwch
    -0.45
    AsUp
    -0.43
    quehanna
    -0.43
    inSlope
    -0.42
    RTEE
    -0.42
    afterEach
    -0.41
    POSITIVE LOGITS
    ipot
    0.40
     tevreden
    0.39
    AndEndTag
    0.39
     spesa
    0.38
    guém
    0.36
    invokeLater
    0.36
    ="@+
    0.35
     wikipagina
    0.35
    исленность
    0.35
     reprodução
    0.35
    Act Density 0.401%

    No Known Activations