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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Best
    -0.07
    Potential
    -0.07
     fiction
    -0.07
    924
    -0.06
     Cao
    -0.06
    Excel
    -0.06
    	case
    -0.06
     Razor
    -0.06
    átní
    -0.06
     funk
    -0.06
    POSITIVE LOGITS
    σμα
    0.07
     cleaned
    0.06
    >{{
    0.06
     modne
    0.06
     مرب
    0.06
    ैट
    0.06
     rules
    0.06
    ğit
    0.06
    _UNS
    0.06
    <dd
    0.06
    Act Density 0.105%

    No Known Activations