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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _shutdown
    -0.09
     Madness
    -0.08
    _fixture
    -0.08
     madness
    -0.08
     shutdown
    -0.08
    _point
    -0.07
    公众
    -0.07
    .shutdown
    -0.07
    shutdown
    -0.07
    _poll
    -0.07
    POSITIVE LOGITS
     Zelda
    0.12
     adventures
    0.12
     tales
    0.11
     tale
    0.10
     quests
    0.10
     RPG
    0.10
     legends
    0.10
     Tolkien
    0.10
     quest
    0.10
     aventuras
    0.10
    Act Density 0.012%

    No Known Activations