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

    Neuronpedia

    INDEX
    Explanations

    Really

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (ne
    -0.06
     회사
    -0.06
    ">{
    -0.06
    Live
    -0.06
     Ast
    -0.06
     expecting
    -0.06
     Gä
    -0.06
     справа
    -0.06
    ект
    -0.06
    /St
    -0.06
    POSITIVE LOGITS
     forcing
    0.07
     SERIES
    0.06
     cinnamon
    0.06
    -trash
    0.06
    -dominated
    0.06
     Unless
    0.06
     Grimm
    0.06
    .token
    0.06
     fodder
    0.06
     chiếc
    0.06
    Act Density 0.009%

    No Known Activations