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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions involving derivatives and their terms

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

    Polynomial and factorization related terms

    np_acts-logits-general · gemini-2.0-flash

    polynomial derivatives and factoring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.66
     TType
    -0.55
    hésite
    -0.48
     saus
    -0.47
     mapStateToProps
    -0.47
    BeforeEach
    -0.46
    ambia
    -0.46
    godic
    -0.45
    egt
    -0.45
     Tab
    -0.45
    POSITIVE LOGITS
     polynomial
    0.79
     polynomials
    0.77
     factorization
    0.77
     Polynomial
    0.77
    Polynomial
    0.75
     factoring
    0.68
     cytok
    0.68
     Polyn
    0.67
    ViewImports
    0.67
     factored
    0.66
    Act Density 1.605%

    No Known Activations