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

    Neuronpedia

    INDEX
    Explanations

    naturally

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     obvious
    -0.98
     obviously
    -0.93
     naturally
    -0.79
    obviously
    -0.79
     Naturally
    -0.77
    Obviously
    -0.75
     Obviously
    -0.74
    Naturally
    -0.74
    obvious
    -0.70
    Obvious
    -0.69
    POSITIVE LOGITS
     propOrder
    1.21
     AssemblyProduct
    0.82
    ContentAsync
    0.80
    tagHelperRunner
    0.79
     IBOutlet
    0.78
     jScrollPane
    0.75
     devriez
    0.75
    ///</
    0.74
    LookAnd
    0.73
    IVEREF
    0.72
    Act Density 0.043%

    No Known Activations