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

    Neuronpedia

    INDEX
    Explanations

    programming code text

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     glyc
    0.57
    ABLES
    0.57
    وار
    0.55
     calorimetry
    0.55
     soles
    0.55
     muque
    0.52
     sulfates
    0.51
     மட
    0.50
    ínsula
    0.50
    靴
    0.50
    POSITIVE LOGITS
     Nag
    1.45
     Naga
    1.40
    Nag
    1.35
     nag
    1.05
    nag
    1.00
     నాగ
    0.93
     நாக
    0.91
     NAG
    0.90
     Loth
    0.87
     Koh
    0.86
    Act Density 0.008%

    No Known Activations