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

    Neuronpedia

    INDEX
    Explanations

    code endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     사람
    0.36
    พ
    0.33
     sheath
    0.31
     aspen
    0.30
     cornice
    0.30
     codons
    0.29
    مله
    0.29
    طان
    0.29
     impresa
    0.29
    дьми
    0.29
    POSITIVE LOGITS
    ↵↵
    0.62
    ↵↵↵↵
    0.54
    ↵↵↵
    0.53
    ↵↵↵↵↵
    0.51
     Furthermore
    0.48
    ↵↵↵↵↵↵
    0.44
    ↵
    0.43
     Additionally
    0.42
          
    0.41
              
    0.41
    Act Density 0.759%

    No Known Activations