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

    Neuronpedia

    INDEX
    Explanations

    evil secrets and scientists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     memories
    -0.07
     discarded
    -0.07
     dictionary
    -0.07
    ۳۶
    -0.06
     FORWARD
    -0.06
     spectrum
    -0.06
    Sure
    -0.06
    КО
    -0.06
     capability
    -0.06
    鬼
    -0.06
    POSITIVE LOGITS
     pract
    0.06
    stantiate
    0.06
    Uvs
    0.06
     quản
    0.06
    olet
    0.06
     cameo
    0.06
    】,【
    0.06
        
    0.06
    >(*
    0.06
     gerek
    0.06
    Act Density 0.092%

    No Known Activations