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

    Neuronpedia

    INDEX
    Explanations

    total number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     możemy
    0.43
     voidaan
    0.43
    جز
    0.40
     obi
    0.40
     possiamo
    0.40
     kolay
    0.39
     diventa
    0.39
     viene
    0.38
     zorgt
    0.38
     matemat
    0.38
    POSITIVE LOGITS
     enlisted
    0.43
     whereupon
    0.42
    面向
    0.40
     necessitating
    0.40
     Featuring
    0.38
     OnePlus
    0.38
     providing
    0.38
    ointment
    0.37
     మండల
    0.37
    providing
    0.37
    Act Density 0.001%

    No Known Activations