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

    Neuronpedia

    INDEX
    Explanations

    breaking down information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.64
    ™,
    0.58
               
    0.57
             
    0.54
              
    0.52
     কীভাবে
    0.52
    ,
    0.52
     Systems
    0.50
     కీల
    0.49
            
    0.48
    POSITIVE LOGITS
     be
    0.57
     sebagainya
    0.51
    好
    0.50
    ไม่มี
    0.50
    𝙘
    0.47
     postpaid
    0.45
     other
    0.45
    小さい
    0.45
    oretically
    0.45
    ambulance
    0.44
    Act Density 4.626%

    No Known Activations