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

    Neuronpedia

    INDEX
    Explanations

    In

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Screens
    -0.07
    .units
    -0.07
     principle
    -0.06
    Semantic
    -0.06
    プレ
    -0.06
     quis
    -0.06
     seen
    -0.06
     Reporter
    -0.06
    _videos
    -0.06
    inciple
    -0.06
    POSITIVE LOGITS
     dhcp
    0.07
     Hannah
    0.07
    ان
    0.07
    ndon
    0.07
    对他
    0.07
     endl
    0.07
     })(
    0.06
    idan
    0.06
    )r
    0.06
    的要求
    0.06
    Act Density 0.003%

    No Known Activations