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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    meni
    -0.07
    uales
    -0.07
     лю
    -0.06
     استاد
    -0.06
    aniu
    -0.06
    áze
    -0.06
     müz
    -0.06
     enslaved
    -0.06
    при
    -0.06
    ότητας
    -0.06
    POSITIVE LOGITS
    -total
    0.07
     trailer
    0.07
     Motion
    0.07
     Co
    0.07
     nods
    0.07
     Lor
    0.06
     hardwood
    0.06
     Thor
    0.06
    urniture
    0.06
     blows
    0.06
    Act Density 0.003%

    No Known Activations