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

    Neuronpedia

    INDEX
    Explanations

    dates followed by slash

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     সম্মত
    0.42
     następnie
    0.42
    缅
    0.42
    协同
    0.41
    丂
    0.41
     Lehigh
    0.40
    AddModelError
    0.40
    ্ি
    0.40
    Aeonium
    0.39
    薢
    0.39
    POSITIVE LOGITS
    uren
    0.42
     экономических
    0.41
     экономического
    0.38
    KY
    0.38
    UZ
    0.38
     Present
    0.37
    mare
    0.37
    ipi
    0.37
    pdb
    0.37
     CLIENTI
    0.37
    Act Density 0.001%

    No Known Activations