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

    Neuronpedia

    INDEX
    Explanations

    Okay, let's break down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     preferably
    0.35
    ง่าย
    0.35
     solvable
    0.35
     suggest
    0.33
    都可以
    0.33
     simplest
    0.33
     heuristic
    0.33
     refrigerant
    0.33
     generalised
    0.33
     recoil
    0.32
    POSITIVE LOGITS
    AA
    0.41
    The
    0.40
     Nederlandse
    0.39
     የ
    0.39
    Thailand
    0.38
    MA
    0.38
     danske
    0.38
     отмечает
    0.37
     महेंद्र
    0.37
    Ketika
    0.37
    Act Density 0.137%

    No Known Activations