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

    Neuronpedia

    INDEX
    Explanations

    documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ishops
    -0.08
     payments
    -0.08
     Auss
    -0.07
     nghĩa
    -0.07
    (kwargs
    -0.07
    村民
    -0.07
    ishop
    -0.07
     Gott
    -0.07
    илось
    -0.07
    иру
    -0.06
    POSITIVE LOGITS
     Jab
    0.08
    ease
    0.08
     failed
    0.08
     talked
    0.07
    讨厌
    0.07
     dejtingsaj
    0.07
    cea
    0.07
    什么东西
    0.07
    总队
    0.07
     opened
    0.07
    Act Density 0.014%

    No Known Activations