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

    Neuronpedia

    INDEX
    Explanations

    very

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ovanou
    -0.07
    clinic
    -0.07
     pře
    -0.07
    रत
    -0.07
     умень
    -0.06
    suggest
    -0.06
    Universal
    -0.06
    elivery
    -0.06
     edilir
    -0.06
     являются
    -0.06
    POSITIVE LOGITS
     alien
    0.06
     messed
    0.06
     кто
    0.06
    elaide
    0.06
     timing
    0.05
    Equipment
    0.05
    tha
    0.05
     routes
    0.05
     gratis
    0.05
    Have
    0.05
    Act Density 0.141%

    No Known Activations