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

    Neuronpedia

    INDEX
    Explanations

    academia

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mathematical
    -0.84
    Mathematical
    -0.83
    mathematical
    -0.81
    atorics
    -0.76
     MATHEMATICAL
    -0.74
    AddTagHelper
    -0.66
     mathematical
    -0.63
    OOTDTY
    -0.63
     AssemblyTitle
    -0.62
    PreInfinity
    -0.60
    POSITIVE LOGITS
     >=",
    0.66
    BeginContext
    0.57
    DoubleQuotes
    0.50
     Lel
    0.49
     Forming
    0.49
     gun
    0.46
    InvalidProtocol
    0.46
     trinh
    0.46
    eably
    0.46
     swings
    0.45
    Act Density 0.093%

    No Known Activations