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

    Neuronpedia

    INDEX
    Explanations

    achieving goals and overcoming challenges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Administ
    0.43
     ​​​​
    0.42
     COVID
    0.41
    
    0.41
    €™
    0.41
    :-
    0.40
     مُ
    0.40
    聽
    0.40
    COVID
    0.40
      
    0.40
    POSITIVE LOGITS
     socalled
    0.85
     wellknown
    0.68
     longterm
    0.68
     diy
    0.58
     Tshirt
    0.55
     cnc
    0.55
     lcd
    0.54
     builtin
    0.51
     usb
    0.50
     tshirt
    0.50
    Act Density 0.001%

    No Known Activations