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

    Neuronpedia

    INDEX
    Explanations

    slot machines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >y
    -0.06
    leen
    -0.06
    CU
    -0.06
    mys
    -0.06
     ML
    -0.06
    izon
    -0.06
     Logan
    -0.06
            	↵
    -0.06
     Either
    -0.06
     Kids
    -0.06
    POSITIVE LOGITS
    μος
    0.07
    ации
    0.06
    รอง
    0.06
    ��
    0.06
     */,
    0.06
     reife
    0.06
     образ
    0.06
    ीफ
    0.06
    ších
    0.06
     avalanche
    0.06
    Act Density 0.015%

    No Known Activations