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

    Neuronpedia

    INDEX
    Explanations

    common measure, usual suspects, primary way

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
             
    0.22
                     
    0.19
         
    0.19
               
    0.19
                 
    0.18
                             
    0.18
     zowel
    0.18
    =
    0.18
     Moż
    0.17
     евре
    0.17
    POSITIVE LOGITS
     conundrum
    0.24
     predicament
    0.23
     dilemma
    0.21
     contender
    0.20
     idea
    0.19
     way
    0.19
     absurdity
    0.19
     crux
    0.18
     ailment
    0.18
     idiom
    0.18
    Act Density 0.648%

    No Known Activations