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

    Neuronpedia

    INDEX
    Explanations

    acknowledging understanding for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ходу
    0.49
    ͹
    0.48
    yld
    0.47
    ोरा
    0.47
    ికె
    0.47
    Edge
    0.45
    垦
    0.45
     ಹೊಂದ
    0.44
    um
    0.44
     Scheduler
    0.44
    POSITIVE LOGITS
                
    0.62
                    
    0.53
     jurídica
    0.48
     från
    0.47
    :
    0.46
     المنت
    0.46
     vutta
    0.45
    ل
    0.45
                        
    0.44
     জাম
    0.44
    Act Density 0.000%

    No Known Activations