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

    Neuronpedia

    INDEX
    Explanations

    Interviews and conversations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    }
↵
↵
↵
↵
    -0.06
    ouden
    -0.06
     },
↵
↵
    -0.06
     žalob
    -0.06
    			
↵			
↵
    -0.06
    388
    -0.06
    oppins
    -0.06
    498
    -0.06
        
↵
↵
    -0.06
     blurry
    -0.06
    POSITIVE LOGITS
     radioactive
    0.07
     Tall
    0.07
     тро
    0.07
     Provided
    0.07
     kl
    0.07
     relation
    0.07
     vacancies
    0.06
     Islanders
    0.06
     мин
    0.06
     гал
    0.06
    Act Density 0.068%

    No Known Activations