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

    Neuronpedia

    INDEX
    Explanations

    search and consult information sources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     deterioration
    0.32
     மாற்றம்
    0.31
     sheath
    0.31
     carbur
    0.30
     granule
    0.30
     feasible
    0.29
     deterior
    0.29
     richness
    0.29
     reconfiguration
    0.29
     boucle
    0.29
    POSITIVE LOGITS
     YouTube
    0.55
     Google
    0.53
     websites
    0.51
     Youtube
    0.50
     Wikipedia
    0.50
     website
    0.49
     newspapers
    0.49
     유튜브
    0.47
     textbooks
    0.46
     literature
    0.45
    Act Density 0.316%

    No Known Activations