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

    Neuronpedia

    INDEX
    Explanations

    list operations and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     इलाज
    0.54
     décès
    0.53
     líquidos
    0.51
     چھوٹے
    0.51
    aien
    0.51
    isées
    0.50
     किती
    0.50
    ٹے
    0.50
     utilisant
    0.50
    eritud
    0.49
    POSITIVE LOGITS
     of
    0.55
     H
    0.52
    -
    0.52
     M
    0.50
     E
    0.49
     T
    0.46
     B
    0.45
     nurture
    0.45
     O
    0.43
     W
    0.43
    Act Density 0.008%

    No Known Activations