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

    Neuronpedia

    INDEX
    Explanations

    C++ libraries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Assembl
    -0.09
     nggawe
    -0.08
     silic
    -0.08
     interessantes
    -0.08
     tinct
    -0.08
    ándole
    -0.08
     caractéristiques
    -0.08
     reservoirs
    -0.08
     Menteri
    -0.08
     plastik
    -0.08
    POSITIVE LOGITS
    规律
    0.08
     Freud
    0.08
     Coffee
    0.08
    roma
    0.07
     coffee
    0.07
     Static
    0.07
     STATIC
    0.07
    obody
    0.07
    iniz
    0.07
     Fahrenheit
    0.07
    Act Density 0.004%

    No Known Activations