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

    Neuronpedia

    INDEX
    Explanations

    the secret to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    好
    0.38
    匂
    0.36
     വിഷയ
    0.36
     పరిస్థి
    0.36
     curvatures
    0.36
    味道
    0.35
     adjoining
    0.35
     lymph
    0.34
    安心
    0.34
     सुविधाओं
    0.34
    POSITIVE LOGITS
     Mistakes
    0.45
     Myths
    0.44
     mistaken
    0.43
     ‌
    0.43
     mistakes
    0.43
    ‌
    0.43
    Secret
    0.42
     Checklist
    0.41
     Snowden
    0.40
    秘
    0.40
    Act Density 0.001%

    No Known Activations