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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    '>↵
    -0.08
    }>↵
    -0.07
    )))));
↵
    -0.07
    污染
    -0.07
    )}↵↵
    -0.07
    "))↵↵
    -0.07
    .")↵↵
    -0.07
    ')}}↵
    -0.06
    }
↵
    -0.06
    "]]↵
    -0.06
    POSITIVE LOGITS
    	cache
    0.08
     미국
    0.07
    加息
    0.07
    igy
    0.07
     conflicts
    0.07
     Asian
    0.07
    GetProperty
    0.07
     Missile
    0.07
    られます
    0.07
    sylvania
    0.06
    Act Density 0.030%

    No Known Activations