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

    Neuronpedia

    INDEX
    Explanations

    deployment configuration descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Comedy
    0.43
     hakim
    0.41
     وقع
    0.36
     Party
    0.36
     संपन्न
    0.36
     variété
    0.35
    했고
    0.35
    Comedy
    0.35
    结算
    0.35
    Hum
    0.35
    POSITIVE LOGITS
    deployment
    0.50
    descriptor
    0.46
    descriptors
    0.46
    ứa
    0.46
     deployment
    0.45
    容器
    0.45
     деклара
    0.44
    packaging
    0.43
     declar
    0.43
     init
    0.42
    Act Density 0.002%

    No Known Activations