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

    Neuronpedia

    INDEX
    Explanations

    written

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     membres
    -0.08
     Meg
    -0.07
    monthly
    -0.07
     toc
    -0.07
    "You
    -0.07
    /mod
    -0.07
     modele
    -0.07
     prophet
    -0.07
    -generic
    -0.07
     crossword
    -0.07
    POSITIVE LOGITS
    휙
    0.07
    ONT
    0.07
     HERO
    0.07
    胃口
    0.07
    六合
    0.07
    这样一来
    0.06
    SION
    0.06
    اه
    0.06
    yster
    0.06
    날
    0.06
    Act Density 0.215%

    No Known Activations