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

    Neuronpedia

    INDEX
    Explanations

    foreign objects, recall, pack, disease

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hymns
    0.38
    ernacle
    0.38
     erythrocytes
    0.38
     tuberc
    0.38
     endothelium
    0.37
     healthful
    0.37
     calomel
    0.36
     syphilit
    0.35
     vesicles
    0.35
     splen
    0.35
    POSITIVE LOGITS
    un
    0.32
     Negoti
    0.32
    do
    0.31
     Just
    0.30
    í
    0.30
    ate
    0.30
    just
    0.30
     proactively
    0.29
     Öncelikle
    0.29
    uncur
    0.28
    Act Density 0.000%

    No Known Activations