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

    Neuronpedia

    INDEX
    Explanations

    core

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hra
    -0.07
     bán
    -0.07
     ();↵
    -0.06
    (cookie
    -0.06
     feat
    -0.06
     comm
    -0.06
     sacr
    -0.06
     paran
    -0.06
     Empty
    -0.06
    lip
    -0.06
    POSITIVE LOGITS
     core
    0.08
    ulu
    0.07
     nutshell
    0.07
    ///<
    0.07
    nette
    0.07
     транспорт
    0.06
     совет
    0.06
     essence
    0.06
    navbarDropdown
    0.06
    izada
    0.06
    Act Density 0.014%

    No Known Activations