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

    Neuronpedia

    INDEX
    Explanations

    variable assignments and declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     corrente
    0.45
     couleur
    0.42
     tecn
    0.41
     செய்தனர்
    0.40
     conferencia
    0.40
     óleo
    0.40
     berwarna
    0.38
     estés
    0.38
     produits
    0.38
     palud
    0.38
    POSITIVE LOGITS
     найбіль
    0.40
    手
    0.39
     Monitor
    0.38
     वह
    0.38
    CREATE
    0.38
     Partnership
    0.38
     earliest
    0.37
     সর্বপ্রথম
    0.37
    ಬಹುದ
    0.36
    根据
    0.36
    Act Density 0.030%

    No Known Activations