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

    Neuronpedia

    INDEX
    Explanations

    Worldometer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reparación
    1.05
     incorporación
    1.01
     formación
    1.00
     separación
    0.98
    wahl
    0.97
    
    0.96
    Hozz
    0.96
     vuelo
    0.95
    redni
    0.94
    aringan
    0.94
    POSITIVE LOGITS
    ت
    1.28
    ب
    1.26
    т
    1.15
     ngược
    1.10
    t
    1.08
    й
    1.05
    s
    1.04
    ד
    1.03
    o
    1.01
    ع
    1.00
    Act Density 0.000%

    No Known Activations