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
     cousins
    -0.07
    (gt
    -0.06
     storyline
    -0.06
     screenshots
    -0.06
     dese
    -0.06
    isten
    -0.06
    info
    -0.06
    contenido
    -0.06
    Numero
    -0.06
    gatsby
    -0.06
    POSITIVE LOGITS
    amat
    0.07
     ***/↵
    0.07
                    ↵↵
    0.07
     explaining
    0.07
         ↵↵
    0.06
    			↵↵
    0.06
     】
    0.06
    科技有限公司
    0.06
     Česká
    0.06
    		
↵		
↵
    0.06
    Act Density 0.028%

    No Known Activations