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

    Neuronpedia

    INDEX
    Explanations

    numbered lists and bullet points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     halves
    0.29
     regimes
    0.28
     encoders
    0.27
    ুখী
    0.27
     tensor
    0.26
     immor
    0.26
     dielectric
    0.25
     indexing
    0.25
    ीडियो
    0.25
    ैमर
    0.24
    POSITIVE LOGITS
      
    0.34
       
    0.29
    -->
    0.29
    Note
    0.29
    ↵↵↵↵↵
    0.29
    note
    0.29
    This
    0.27
    ↵↵↵↵
    0.27
    **
    0.26
    These
    0.26
    Act Density 0.911%

    No Known Activations