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

    Neuronpedia

    INDEX
    Explanations

    command-line syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     группы
    -0.10
     মিনিট
    -0.09
    -conditioned
    -0.09
    ировки
    -0.09
    -En
    -0.09
     ответа
    -0.08
     그룹
    -0.08
     ambassadors
    -0.08
     ответственности
    -0.08
     firmy
    -0.08
    POSITIVE LOGITS
    Installed
    0.09
    installed
    0.08
    gom
    0.08
    globals
    0.08
    peng
    0.08
    Lua
    0.08
    idem
    0.08
    pag
    0.08
    Navig
    0.08
    defs
    0.08
    Act Density 0.015%

    No Known Activations