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

    Neuronpedia

    INDEX
    Explanations

    timing the next action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    restaurants
    0.53
    ರಿಂದ
    0.47
    Parliament
    0.45
    ride
    0.45
    Restaurants
    0.44
    customers
    0.44
    riminating
    0.44
     рестора
    0.43
     публи
    0.43
    われている
    0.43
    POSITIVE LOGITS
     initial
    0.45
     recoil
    0.43
     Gine
    0.43
     chock
    0.42
    具
    0.42
    ลำ
    0.41
    டுக்க
    0.41
     schematically
    0.40
     contoh
    0.40
     Malin
    0.40
    Act Density 0.001%

    No Known Activations