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

    Neuronpedia

    INDEX
    Explanations

    the presence of mathematical and computational terms related to neighbor relationships in data

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

    Mathematical or code-related expressions

    np_acts-logits-general · gemini-2.0-flash

    neighbours and dimensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     przep
    -0.53
    JspWriter
    -0.52
     Drapeau
    -0.52
    oneofs
    -0.51
    InstrumentedTest
    -0.50
     descri
    -0.49
     Chwiliwch
    -0.48
    EDEFAULT
    -0.47
     describir
    -0.47
    ˈ
    -0.46
    POSITIVE LOGITS
     squares
    0.73
     square
    0.69
     Square
    0.65
     AssemblyCulture
    0.64
     SQUARE
    0.63
     grid
    0.62
    Square
    0.60
     الاطلاع
    0.60
     GridView
    0.60
    square
    0.59
    Act Density 0.490%

    No Known Activations