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

    Neuronpedia

    INDEX
    Explanations

    mathematical structures and formatting related to matrix and alignment in equations

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

    aligned block end

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.90
    RegressionTest
    -0.79
     Italijanski
    -0.79
     queſta
    -0.77
     miniaturka
    -0.76
     noDo
    -0.72
    pecabe
    -0.71
    genodigd
    -0.70
     Geſch
    -0.70
     saveiro
    -0.69
    POSITIVE LOGITS
    center
    0.51
    Centre
    0.49
    centre
    0.47
    Center
    0.42
     centre
    0.41
     Centre
    0.40
    stand
    0.37
    :
    0.36
     AssemblyCompany
    0.36
    ,
    0.35
    Act Density 0.006%

    No Known Activations