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

    Neuronpedia

    INDEX
    Explanations

    Reduced blood

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ุ
    1.00
     ૩
    0.99
    อนุ
    0.96
     reporting
    0.94
    一個
    0.92
     அரசு
    0.91
    Reporting
    0.91
     ജില്ലാ
    0.91
     разбира
    0.90
    调查
    0.90
    POSITIVE LOGITS
     lysates
    1.06
     phosphat
    1.05
    >′
    0.98
     morceau
    0.96
     protr
    0.95
     seams
    0.94
     unleash
    0.94
     combust
    0.93
    issimo
    0.93
    ophan
    0.92
    Act Density 0.004%

    No Known Activations