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

    Neuronpedia

    INDEX
    Explanations

    SQL statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hydrolysis
    0.40
     vallée
    0.38
     sculptural
    0.38
     یا
    0.37
     thermodynam
    0.37
     polypes
    0.37
    Voids
    0.37
     volatil
    0.37
     azal
    0.37
     Maugin
    0.37
    POSITIVE LOGITS
    ↵
    0.50
        
    0.49
         
    0.47
    ıc
    0.46
    it
    0.44
            
    0.42
    0.41
             
    0.39
    ਾ
    0.39
    iostream
    0.38
    Act Density 0.615%

    No Known Activations