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

    Neuronpedia

    INDEX
    Explanations

    specific programming constructs, functions, or method calls in code

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

    ch followed by stone, ASP followed by NET

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.76
     betweenstory
    -0.75
    RegressionTest
    -0.71
     GenerationType
    -0.68
    astify
    -0.68
    transQ
    -0.66
    IntoConstraints
    -0.63
    aarrggbb
    -0.60
    tableFuture
    -0.59
    FunctionFlags
    -0.57
    POSITIVE LOGITS
     world
    0.39
     wanna
    0.38
    Panamoan
    0.38
    kuš
    0.35
     cozin
    0.35
     widgets
    0.34
    Matrix
    0.34
     Middle
    0.34
     concept
    0.34
     apps
    0.33
    Act Density 0.005%

    No Known Activations