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

    Neuronpedia

    INDEX
    Explanations

    identifying options and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OV
    0.41
    H
    0.41
    co
    0.40
    C
    0.38
    Hp
    0.38
     सौदा
    0.38
     concession
    0.37
    util
    0.37
    cost
    0.37
    X
    0.37
    POSITIVE LOGITS
     ব্যবস
    0.41
     اسمه
    0.41
     حرم
    0.40
    نې
    0.40
    اخ
    0.39
     historia
    0.38
     colorChoice
    0.38
     Ayala
    0.38
     آسیب
    0.38
     प्रतिबंधित
    0.38
    Act Density 0.000%

    No Known Activations