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

    Neuronpedia

    INDEX
    Explanations

    assignments and parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    性和
    0.43
    chées
    0.41
    abhavam
    0.41
    ikiran
    0.40
    Türk
    0.39
    чні
    0.39
     далее
    0.39
    média
    0.38
    טורק
    0.38
    ższe
    0.38
    POSITIVE LOGITS
     counterpart
    0.65
     equally
    0.60
      
    0.46
    ↵↵
    0.44
     counterparts
    0.43
        
    0.42
    ↵
    0.41
    .
    0.41
     I
    0.41
       
    0.40
    Act Density 0.531%

    No Known Activations