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

    Neuronpedia

    INDEX
    Explanations

    no-fault insurance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fortn
    -0.08
    懊
    -0.07
    答卷
    -0.07
     Garmin
    -0.07
    拃
    -0.07
     acknowled
    -0.07
    ケット
    -0.07
    Fight
    -0.07
    꿩
    -0.07
    茄子
    -0.07
    POSITIVE LOGITS
    lying
    0.07
    μ
    0.07
     ("
    0.06
     pure
    0.06
    asions
    0.06
    'b
    0.06
    בוה
    0.06
    %.↵↵
    0.06
     wondering
    0.06
    鸟类
    0.06
    Act Density 0.010%

    No Known Activations