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

    Neuronpedia

    INDEX
    Explanations

    say "s" word

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IPPING
    -0.07
     podcast
    -0.07
     balances
    -0.07
    contest
    -0.07
    hud
    -0.07
    pard
    -0.07
    pedo
    -0.07
    /bash
    -0.07
    琔
    -0.06
    .ylim
    -0.06
    POSITIVE LOGITS
     الأ
    0.07
    する
    0.07
     Worse
    0.07
     giảm
    0.07
    来看
    0.07
     incremental
    0.07
    城市建设
    0.07
    >",
    0.07
    }()↵↵
    0.07
    .M
    0.07
    Act Density 0.003%

    No Known Activations