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

    Neuronpedia

    INDEX
    Explanations

    policing and auditing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.96
     pleaſure
    -0.94
     Majefty
    -0.93
     myſelf
    -0.93
    RenderAtEndOf
    -0.93
     transfieras
    -0.91
    ViewFeatures
    -0.90
     виправивши
    -0.90
     reaſon
    -0.90
     flesta
    -0.90
    POSITIVE LOGITS
     a
    0.61
     the
    0.59
    ly
    0.59
     ana
    0.49
     M
    0.49
    DebuggerNonUser
    0.48
     E
    0.48
     
    0.48
     P
    0.47
     Mat
    0.47
    Act Density 0.459%

    No Known Activations