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

    Neuronpedia

    INDEX
    Explanations

    feature

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
        
    1.49
       
    1.49
         
    1.42
          
    1.29
           
    1.22
            
    0.88
     ..
    0.88
    ..
    0.87
    ....
    0.85
    .....
    0.84
    POSITIVE LOGITS
    ……………………
    1.24
    ................
    1.24
    ----------------
    1.23
     ……………………
    1.23
    ………………………………
    1.20
    ________________
    1.16
    ————————
    1.13
    ————————————————
    1.12
    ****************
    1.12
    ━━━━━━━━
    1.12
    Act Density 0.252%

    No Known Activations