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

    Neuronpedia

    INDEX
    Explanations

    Mass/weight

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arians
    -0.07
     prevailed
    -0.07
    ased
    -0.07
    erties
    -0.07
    Csv
    -0.07
    yen
    -0.07
    िह
    -0.07
     sensitive
    -0.06
    овани
    -0.06
     confidence
    -0.06
    POSITIVE LOGITS
    		
↵		
↵
    0.07
     *));↵
    0.07
    mg
    0.07
    )))↵
    0.07
     mg
    0.07
    ])]↵
    0.07
    )]↵
    0.07
     }
↵
↵
↵
    0.07
    Mrs
    0.06
    --}}↵
    0.06
    Act Density 0.003%

    No Known Activations