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

    Neuronpedia

    INDEX
    Explanations

    !

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     User
    0.54
     Administrat
    0.53
    ]}"
    0.53
    ಂಡ
    0.52
     lounges
    0.50
     workspaces
    0.50
     Anwendung
    0.49
    island
    0.49
     Yours
    0.49
     Verwaltung
    0.49
    POSITIVE LOGITS
    了一个
    0.73
    了一個
    0.70
     בכ
    0.68
     một
    0.67
     една
    0.67
     një
    0.66
     isang
    0.66
     一个
    0.66
    一个
    0.64
     ਇੱਕ
    0.63
    Act Density 0.001%

    No Known Activations