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

    Neuronpedia

    INDEX
    Explanations

    Algebraic Thinking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    يمه
    0.49
    Dinner
    0.41
    晚餐
    0.39
     constantes
    0.39
    לות
    0.37
    சனம்
    0.37
    アシ
    0.37
    friday
    0.37
    IndexPath
    0.37
    分鐘
    0.37
    POSITIVE LOGITS
     measuring
    0.49
     maneuvering
    0.45
     manoeuv
    0.45
     Riv
    0.44
     nearing
    0.43
     Bea
    0.42
     yawning
    0.41
     formulated
    0.40
     नाइन
    0.40
    📘
    0.40
    Act Density 0.000%

    No Known Activations